{ "complete": true, "report": { "bucket": "emo_Emotional_Numbness", "label": "Intense Emotional Numbness", "definition": { "id": "emo_Emotional_Numbness", "category": "emotion", "head": "emo_Emotional_Numbness", "pole": "high", "label": "Intense Emotional Numbness", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_emotional_numbness/full-v2-sealed/sealed-selected", "mission": "emotion_emotional_numbness", "format_status": "CANONICAL", "heldout": true, "qualified": true, "source_cfg": 3, "source_model": { "label": "Humaneness 1.5 + real-speech rank 4", "repo": "laion/Humaneness-Voice-Large-1.5-RealSpeech-LoRAs", "revision": "fed33e554f094fcdc89fc0124aed2f9d42018714", "rank": 4 }, "metrics": { "ce": 6.2276934099197385, "genuineness": 4.565965347290039, "wer": 0.011973773063942697, "identity": 0.6104406780004501, "voiceclap": 0.07000999961048365, "fitness": 0.6122317878942756, "steering_v2": 0.5476984764945237, "raw_target": 0.5865919069945812, "target_cdf": 0.5476984764945237, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.236430349349976, "genuineness": 4.570735130310059, "wer": 0.014242888049339661, "identity": 0.6104406780004501, "fitness": 0.6116704275758891, "steering_v2": 0.5487885348563544 }, "none": { "n": 50, "ce": 6.218956470489502, "genuineness": 4.56119556427002, "wer": 0.009704658078545732, "identity": null, "fitness": 0.6127931482126621, "steering_v2": 0.5466084181326932 } } } } ], "selected_wording": { "id": "manual-53d14c32a3a7", "general": "Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.", "inline": [ "Initiate with a breathy, minimal vocal projection that suggests detachment.", "Sustain a mid-range, unchanging vocal placement across the core of the statement.", "Deliver the closing words with the same low energy, ensuring no rise or fall." ], "cfg": 3, "recipe": "P05", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 0.10073852379613912, "target_raw": 0.5586809828877449, "ce": 5.705502462387085, "genuineness": 4.555986404418945, "identity": 0.5716709911823272, "wer": 0.008187134502923975, "valid_fraction": 1, "identity_delta": -0.011903558671474457, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 0.11927490507866788, "target_raw": 0.576503086835146, "ce": 5.6605271100997925, "genuineness": 4.596153092384339, "identity": 0.5571686305105686, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.02640591934323311, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 0.10073852379613912, "target_raw": 0.5586809828877449, "ce": 5.705502462387085, "genuineness": 4.555986404418945, "identity": 0.5716709911823272, "wer": 0.008187134502923975, "valid_fraction": 1, "identity_delta": -0.011903558671474457, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 0.05980835348018434, "target_raw": 0.5193280078470707, "ce": 5.84072642326355, "genuineness": 4.622826266288757, "identity": 0.6077699474990368, "wer": 0.014930555555555555, "valid_fraction": 0.95, "identity_delta": 0.02419539764523506, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.0622955299718066, "target_raw": 0.40192925184965134, "ce": 5.927897262573242, "genuineness": 4.595525407791138, "identity": 0.5927352741360664, "wer": 0.005718954248366013, "valid_fraction": 1, "identity_delta": 0.00916072428226471, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": -0.11785888697756071, "target_raw": 0.3485069625079632, "ce": 6.03234338760376, "genuineness": 4.593328857421875, "identity": 0.5841721907258034, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.000597640872001648, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": -0.20817871201209417, "target_raw": 0.2616675041615963, "ce": 6.004941153526306, "genuineness": 4.523351001739502, "identity": 0.6128637149930001, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.029289165139198305, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -0.21323242518656632, "target_raw": 0.25680852979421614, "ce": 6.109387278556824, "genuineness": 4.499188256263733, "identity": 0.574329187721014, "wer": 0.006666666666666666, "valid_fraction": 1, "identity_delta": -0.009245362132787704, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -0.2671020464299003, "target_raw": 0.20501471012830735, "ce": 6.104423141479492, "genuineness": 4.530882263183594, "identity": 0.5503679752349854, "wer": 0.00804093567251462, "valid_fraction": 1, "identity_delta": -0.033206574618816376, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.31323242363672904, "target_raw": 0.1606619119644165, "ce": 6.1826584815979, "genuineness": 4.498874521255493, "identity": 0.5752950668334961, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.008279483020305633, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 0.11927490507866788, "target_raw": 0.576503086835146, "ce": 5.6605271100997925, "genuineness": 4.596153092384339, "identity": 0.5571686305105686, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.02640591934323311, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 0.11267089667879795, "target_raw": 0.5701535560190678, "ce": 5.690212869644165, "genuineness": 4.587052798271179, "identity": 0.5705093026161194, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.013065247237682343, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 0.09298096455794984, "target_raw": 0.5512223519384861, "ce": 5.815409135818482, "genuineness": 4.612156963348388, "identity": 0.5936783894896507, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": 0.010103839635848998, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 0.07124633602976084, "target_raw": 0.5303252413868904, "ce": 5.719302845001221, "genuineness": 4.624081468582153, "identity": 0.5845248609781265, "wer": 0.006274509803921568, "valid_fraction": 1, "identity_delta": 0.0009503111243247986, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 0.03695068730942427, "target_raw": 0.4973511345684528, "ce": 5.80438871383667, "genuineness": 4.613412213325501, "identity": 0.5976956091821194, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.014121059328317642, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 0.03264770909877212, "target_raw": 0.4932139664888382, "ce": 5.805580091476441, "genuineness": 4.61403980255127, "identity": 0.6097487896680832, "wer": 0.008333333333333333, "valid_fraction": 0.95, "identity_delta": 0.026174239814281464, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": -0.004162600926951461, "target_raw": 0.45782209783792494, "ce": 5.944775414466858, "genuineness": 4.583600974082946, "identity": 0.5982688225805759, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.014694272726774215, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": -0.0060668929284398, "target_raw": 0.45599118545651435, "ce": 5.929485821723938, "genuineness": 4.598663473129273, "identity": 0.6075574085116386, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.023982858657836913, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": -0.029209895760426402, "target_raw": 0.43373997062444686, "ce": 5.9690005540847775, "genuineness": 4.620002007484436, "identity": 0.6198537789285183, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.03627922907471657, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": -0.04364623994605078, "target_raw": 0.4198599137365818, "ce": 5.967809176445007, "genuineness": 4.593015050888061, "identity": 0.6071762047708035, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.023601654917001724, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": -0.08075561664118527, "target_raw": 0.3841805025935173, "ce": 5.960660791397094, "genuineness": 4.65357882976532, "identity": 0.6160931780934333, "wer": 0.0061111111111111106, "valid_fraction": 1, "identity_delta": 0.032518628239631656, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": -0.1185302718240952, "target_raw": 0.34786144867539404, "ce": 5.971383380889892, "genuineness": 4.5864252090454105, "identity": 0.6039377599954605, "wer": 0.008742690058479531, "valid_fraction": 1, "identity_delta": 0.02036321014165878, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": -0.1601745637487116, "target_raw": 0.3078218698501587, "ce": 6.06192979812622, "genuineness": 4.555045008659363, "identity": 0.6099542587995529, "wer": 0.016884889920880632, "valid_fraction": 1, "identity_delta": 0.02637970894575119, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": -0.1827636741210532, "target_raw": 0.2861032038927078, "ce": 6.040286016464234, "genuineness": 4.600860047340393, "identity": 0.5996233396232128, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": 0.016048789769411088, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": -0.1902099617214997, "target_raw": 0.2789438501000404, "ce": 6.015068078041077, "genuineness": 4.553162217140198, "identity": 0.5982092142105102, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.014634664356708526, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.21735839958474282, "target_raw": 0.25284154489636423, "ce": 6.0990618705749515, "genuineness": 4.528999471664429, "identity": 0.5858049124479294, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.002230362594127655, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.2363647488649922, "target_raw": 0.2345675826072693, "ce": 6.124875521659851, "genuineness": 4.497933077812195, "identity": 0.5892800241708755, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.005705474317073822, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.23754883072218821, "target_raw": 0.23342912793159484, "ce": 6.11713137626648, "genuineness": 4.459335398674011, "identity": 0.5933130063116551, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.009738456457853317, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -0.23942871356193143, "target_raw": 0.2316216841340065, "ce": 6.094494748115539, "genuineness": 4.521154415607453, "identity": 0.6061549723148346, "wer": 0.023993808049535603, "valid_fraction": 0.95, "identity_delta": 0.022580422461032867, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -0.26324462937997956, "target_raw": 0.20872348621487619, "ce": 6.105415964126587, "genuineness": 4.553789806365967, "identity": 0.5923491314053535, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": 0.008774581551551818, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -0.28171996799772064, "target_raw": 0.1909600727260113, "ce": 6.116734266281128, "genuineness": 4.502012538909912, "identity": 0.6003143057227135, "wer": 0.0293859649122807, "valid_fraction": 0.9, "identity_delta": 0.016739755868911743, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.2908935554109592, "target_raw": 0.1821399785578251, "ce": 6.13023681640625, "genuineness": 4.438624429702759, "identity": 0.5591886587440967, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.02438589110970497, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.30123290792987245, "target_raw": 0.1721990406513214, "ce": 6.097274756431579, "genuineness": 4.4499213099479675, "identity": 0.5859767064452172, "wer": 0.0061111111111111106, "valid_fraction": 1, "identity_delta": 0.0024021565914154053, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.3103515621367569, "target_raw": 0.16343176290392875, "ce": 6.164787411689758, "genuineness": 4.5104851722717285, "identity": 0.5530069462954998, "wer": 0.00804093567251462, "valid_fraction": 1, "identity_delta": -0.030567603558301924, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.36303710694732527, "target_raw": 0.11277639269828796, "ce": 6.200529456138611, "genuineness": 4.332873201370239, "identity": 0.5835745498538017, "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": -0.35732421931908087, "target_raw": 0.11826914101839066, "ce": 6.213237738609314, "genuineness": 4.307141423225403, "identity": 0.610950343310833, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.02737579345703125, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.3408203163019445, "target_raw": 0.13413708582520484, "ce": 6.1852398157119755, "genuineness": 4.340090656280518, "identity": 0.5837679177522659, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0001933678984642029, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.35854491763110974, "target_raw": 0.11709548085927964, "ce": 6.188218307495117, "genuineness": 4.294903194904327, "identity": 0.586082249879837, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0025077000260353088, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.33365722441754947, "target_raw": 0.14102415651082992, "ce": 6.246914663314819, "genuineness": 4.376679911613464, "identity": 0.5939327973127365, "wer": 0.01784490871447393, "valid_fraction": 0.98, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 0.11224365009981571, "target_raw": 0.5697427728772163, "ce": 5.808558654785156, "genuineness": 4.639771585464477, "identity": 0.6012379646301269, "wer": 0.025617824204780724, "valid_fraction": 0.96, "identity_delta": 0.007305167317390442, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 0.15911132580145493, "target_raw": 0.614804458618164, "ce": 5.848351392745972, "genuineness": 4.647177286148072, "identity": 0.6096303921937942, "wer": 0.022554607863532347, "valid_fraction": 1, "identity_delta": 0.01569759488105774, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 0.11224365009981571, "target_raw": 0.5697427728772163, "ce": 5.808558654785156, "genuineness": 4.639771585464477, "identity": 0.6012379646301269, "wer": 0.025617824204780724, "valid_fraction": 0.96, "identity_delta": 0.007305167317390442, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.04686767570163923, "ci95_z": [ 0.013994134857910307, 0.10048585041987572 ], "language_deltas": { "en": 0.02226561904281308, "de": 0.003686514171773797, "fr": 0.03190917600360952, "nl": 0.14947511351937912, "es": 0.027001955770620624 }, "languages_improved": 5, "clear_gain": true, "delta_ce": 0.03979273796081543, "delta_genuineness": 0.00740570068359375, "delta_wer": -0.003063216341248378, "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": 0.04686767570163923, "ci95_z": [ 0.013994134857910307, 0.10048585041987572 ], "language_deltas": { "en": 0.02226561904281308, "de": 0.003686514171773797, "fr": 0.03190917600360952, "nl": 0.14947511351937912, "es": 0.027001955770620624 }, "languages_improved": 5, "clear_gain": true, "delta_ce": 0.03979273796081543, "delta_genuineness": 0.00740570068359375, "delta_wer": -0.003063216341248378, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.44590087451736515, "ci95_z": [ 0.3697192370634775, 0.5122949165462236 ], "language_deltas": { "en": 0.3173095696374732, "de": 0.5227294853312864, "fr": 0.3850585909772443, "nl": 0.5116088854277234, "es": 0.49279784121309855 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.4383560085296631, "delta_genuineness": 0.2630916738510132, "delta_wer": 0.007772915490306794, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": true, "scale": 0.5, "cfg": 5.0, "reason": "Held-out target improves against matched CFG and best manual-only configuration; QA passes" }, "reference_only": true, "updated": 1793035108.883342, "example": { "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.", "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." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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.", "language": "de", "seed": 1702, "scale": 0.5, "cfg": 5.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "002681deac44eaeb7945e9aa6431e6e78ea038c0a234ee67ade3b5ed816d6bac", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "023d39f6a202efb5b29b9b12666672a1003dea2604da6a7bdd5f6a91712abc10", "generation_seconds_batch": 26.242445894051343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1313202977180481, "target_z": -0.34374999612540685, "ce": 6.340320587158203, "genuineness": 4.532451152801514, "identity": 0.3229096233844757, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/002681deac44eaeb7945e9aa6431e6e78ea038c0a234ee67ade3b5ed816d6bac.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "0098d8fb4c8584341fa257a8c3ef04ec8b471185b2a5ec6f9e43c59815aedd17", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "75e6b173ecf98d635624a6d6123b31c4c59db09fffd56789b15d7bab16cd815a", "generation_seconds_batch": 24.66411050898023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5444502830505371, "target_z": 0.08593748353297924, "ce": 5.538110733032227, "genuineness": 4.808597087860107, "identity": 0.6093540191650391, "hypothesis": "He encontrado la cajita, estaba junto la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/0098d8fb4c8584341fa257a8c3ef04ec8b471185b2a5ec6f9e43c59815aedd17.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "00aede9654c3b1a9d327f9001c3a1aecacdeebaa6ca5f9e52f0bf432fd7de1ee", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "abdb24e8cb1e1317f9f045486465d2f17f60c7be17a8e382e30fcca270eddb74", "generation_seconds_batch": 23.284962383913808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14822107553482056, "target_z": -0.3261718660400034, "ce": 6.23706579208374, "genuineness": 4.582659721374512, "identity": 0.5150127410888672, "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_Emotional_Numbness/00aede9654c3b1a9d327f9001c3a1aecacdeebaa6ca5f9e52f0bf432fd7de1ee.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "00d0ae937c6f40f3446984276a3311ba0c9462694a60b29be29f98ac179fcc78", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "47e9fbcce2deb54fe7907c7274cc3212cc436c8d6ae8021aea4963e7acc66172", "generation_seconds_batch": 23.082463852944784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14070960879325867, "target_z": -0.3339843786324311, "ce": 6.268836498260498, "genuineness": 4.457139015197754, "identity": 0.44385477900505066, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/00d0ae937c6f40f3446984276a3311ba0c9462694a60b29be29f98ac179fcc78.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "0193a5e55234f6270a755b76a61029e1f43939af0a6c10a14387cd62d119ce70", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "20206f95e24a8b4d7636f7ca0a53d217940ec4c23eef75c0966b04fa7c2796b5", "generation_seconds_batch": 18.518793233088218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42191970348358154, "target_z": -0.04150389759270599, "ce": 6.117925643920898, "genuineness": 4.6956281661987305, "identity": 0.2642778158187866, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/0193a5e55234f6270a755b76a61029e1f43939af0a6c10a14387cd62d119ce70.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "8124e6796dfa6c29066988a9a2e4898945a5dc84ac6385a022b8bf05fac7461b", "generation_seconds_batch": 15.852800325024873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1238088309764862, "target_z": -0.3515625087178345, "ce": 5.911416053771973, "genuineness": 4.570107460021973, "identity": 0.8228473663330078, "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_Emotional_Numbness/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "01ffc91f89a067db5d2679e784efb0356d7e4b4da81b59accf03f72d7dfe84a0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "87d4bc439961cb9e43218ade0b9b6b286c73d729416ae122a07a17eed0e0783c", "generation_seconds_batch": 24.89188087102957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2101905643939972, "target_z": -0.26171875339026895, "ce": 6.372091293334961, "genuineness": 4.406930446624756, "identity": 0.6205021142959595, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/01ffc91f89a067db5d2679e784efb0356d7e4b4da81b59accf03f72d7dfe84a0.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "02bb51cf3db2b92f9bc45a532775cc3a4735c6b30d109b369d89c5a5329e77c6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8f2e6e8f1958985d8d869bb674bd923ef642e01275608462cd4046d6add45a10", "generation_seconds_batch": 22.353348979959264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.215824156999588, "target_z": -0.2558593766951345, "ce": 5.95112943649292, "genuineness": 4.883909225463867, "identity": 0.7146602869033813, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/02bb51cf3db2b92f9bc45a532775cc3a4735c6b30d109b369d89c5a5329e77c6.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "034307eb7ec43af7e320fab7e8de6c6c1b37f75eb8b9c660bd589a722fc6dd4d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9c66635e7f24747d8717efdf9388dd7e25f4addca3bc7cde15fca35c411ac5bd", "generation_seconds_batch": 23.082463852944784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 6.300607204437256, "genuineness": 4.369274139404297, "identity": 0.5629071593284607, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/034307eb7ec43af7e320fab7e8de6c6c1b37f75eb8b9c660bd589a722fc6dd4d.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "0368563a4ffacb46a3897c234aefbb9d3f2a595cce0d96dd08cfc79b95670a9d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0f6777cbd41f1bc482447aef41a0599702ba674303cc304ff9fdbcc6581db506", "generation_seconds_batch": 20.437350912950933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5101792812347412, "target_z": 0.05029296263540773, "ce": 5.514282703399658, "genuineness": 4.337893962860107, "identity": 0.4637843668460846, "hypothesis": "De deur 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_Emotional_Numbness/0368563a4ffacb46a3897c234aefbb9d3f2a595cce0d96dd08cfc79b95670a9d.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "04da3c07ca8b6abd249391df75b052ae4100930eb8527c468bb5e9a971b5aca8", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6bed29e2c0d2ff9956feae427e2aec06ccdfeac402f346fe04879c6b09106db6", "generation_seconds_batch": 24.026338972966187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1463432013988495, "target_z": -0.32812500193729655, "ce": 6.086154937744141, "genuineness": 4.1998209953308105, "identity": 0.27795135974884033, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/04da3c07ca8b6abd249391df75b052ae4100930eb8527c468bb5e9a971b5aca8.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "04f9adc0997703bb3d9b8b05c17b965650ad06d0a1c7c79e20753527b03dd986", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8789e87c1b8942169ad1337086482f943af821fd1e8bf2cc4f1e50fbd1100601", "generation_seconds_batch": 23.116326601943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49468690156936646, "target_z": 0.03417967672378788, "ce": 5.696964263916016, "genuineness": 4.846253395080566, "identity": 0.8116484880447388, "hypothesis": "La porte 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_Emotional_Numbness/04f9adc0997703bb3d9b8b05c17b965650ad06d0a1c7c79e20753527b03dd986.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "6a430e696ca514e6964fa5102bbe3277cf4541906f210de88f43426ba5a05113", "generation_seconds_batch": 18.271035377983935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052450031042099, "target_z": -0.42578123886054475, "ce": 6.459460258483887, "genuineness": 4.808597087860107, "identity": 0.5016905069351196, "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_Emotional_Numbness/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "063d2e92e50471c4adf7ef41d6f7f20a8298410130acf4ef3eed225b33d822fa", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8d17a6ee5e14cef7769ad7535f849e666a1e3467325901f1dbd0388ce1bced61", "generation_seconds_batch": 16.80917611590121, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1388317346572876, "target_z": -0.3359375145297242, "ce": 6.141753673553467, "genuineness": 4.645420074462891, "identity": 0.5082240700721741, "hypothesis": "La porte 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_Emotional_Numbness/063d2e92e50471c4adf7ef41d6f7f20a8298410130acf4ef3eed225b33d822fa.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "0645d9408a2bd02224d30cbeb31f81f6d2f08b4ec3f9d19a62a4b7eb7ebefee0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2cea57c0a89269b821680ac56a158aa1031af15d3e8fa73e310c03701d2a47b4", "generation_seconds_batch": 18.428127496968955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4867059886455536, "target_z": 0.025878903404595678, "ce": 5.673136234283447, "genuineness": 4.444586753845215, "identity": 0.4978342354297638, "hypothesis": "Ik 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_Emotional_Numbness/0645d9408a2bd02224d30cbeb31f81f6d2f08b4ec3f9d19a62a4b7eb7ebefee0.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "06da2ba951d7dade306b06682b00b360c0375c46abae56c0f1b14c57d893a74c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "124b70f3d798f3801de2d553762f4fd6b51864de49146bdfb15dafbddadc9315", "generation_seconds_batch": 18.707334491075017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.435651570558548, "target_z": -0.02722168239668816, "ce": 6.252951145172119, "genuineness": 4.7834930419921875, "identity": 0.3537561297416687, "hypothesis": "I found the little box. It was beside the old window. Lointias inside, together.", "wer": 0.1875, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/06da2ba951d7dade306b06682b00b360c0375c46abae56c0f1b14c57d893a74c.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "0822bfbb52cfa76571afadf94596ae9b464c73d4c610e420942954c45c410cf2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b5c0c01aab1ea8a4012acd4d86af517837fc80799448d9b103d4360dfd1a7fe7", "generation_seconds_batch": 24.184396581957117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27497684955596924, "target_z": -0.1943359523929673, "ce": 6.0305562019348145, "genuineness": 4.632867813110352, "identity": 0.641255259513855, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/0822bfbb52cfa76571afadf94596ae9b464c73d4c610e420942954c45c410cf2.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "091842daacbefc4c19d7b1bfdaeb5f09cd8354f46040b14d071e92429a8caebe", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7ac76565fbbc9f0abd9c46d38f8cb72a3bcf6facc9bf51a99629d67e4552ea77", "generation_seconds_batch": 22.89118132099975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1745111644268036, "target_z": -0.2988281184616241, "ce": 6.070269584655762, "genuineness": 4.632867813110352, "identity": 0.6096146106719971, "hypothesis": "La porte 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_Emotional_Numbness/091842daacbefc4c19d7b1bfdaeb5f09cd8354f46040b14d071e92429a8caebe.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "093dc052bb2b0c4ce40465937f32f16feae5a6d5f586ce9bb47f45a70ec1c529", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d46e3706f4dfe06396da9a43ae52143472216ee1724e46a81eb9ec611bb8bd80", "generation_seconds_batch": 25.961231779074296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2928165793418884, "target_z": -0.17578123886054478, "ce": 6.165581703186035, "genuineness": 4.193545341491699, "identity": 0.6565914154052734, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/093dc052bb2b0c4ce40465937f32f16feae5a6d5f586ce9bb47f45a70ec1c529.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "09bd1d199f599fd0b7a86e1823a64c391c3ab52844a9268ace03188c2c8d318b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4c6bab694c4abe8886ec1417d4e4d286bf7572fe087cef876fe58017d0e55f15", "generation_seconds_batch": 25.03262082999572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5341220498085022, "target_z": 0.07519531358972932, "ce": 5.9431867599487305, "genuineness": 4.3127899169921875, "identity": 0.6679230332374573, "hypothesis": "Ik 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_Emotional_Numbness/09bd1d199f599fd0b7a86e1823a64c391c3ab52844a9268ace03188c2c8d318b.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "0a102ab8297193d46f69c44424d7bc3a008954b203d96c644dcd06a23776a81a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ca64fc3bffed30553a626c0d78386665ff89d09d749d654cd7b938af9ecd9f3c", "generation_seconds_batch": 25.961231779074296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1669996976852417, "target_z": -0.30664063105405176, "ce": 6.109982967376709, "genuineness": 4.607763767242432, "identity": 0.3123052716255188, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/0a102ab8297193d46f69c44424d7bc3a008954b203d96c644dcd06a23776a81a.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "0a7908962cead1d272a036651d700fdeccfd6e59f253c8870f945ac9db295101", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "222636f4911546f314b26bf28b2a415ac9592410640423fa47d164eb9c17fd37", "generation_seconds_batch": 25.227165518910624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24305318295955658, "target_z": -0.22753906116810863, "ce": 6.157639026641846, "genuineness": 4.607763767242432, "identity": 0.7445257902145386, "hypothesis": "La porte 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_Emotional_Numbness/0a7908962cead1d272a036651d700fdeccfd6e59f253c8870f945ac9db295101.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "0a82748e2d7d1dcd70d85f3da709c0725beb537590b7941a8aca492ef63e77f2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c4309c8592f818d75a5e69e483680f21c10f2d97261b6516b0c1e5e9599b499b", "generation_seconds_batch": 19.756263675983064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05808362364768982, "target_z": -0.4199218621654103, "ce": 6.38003396987915, "genuineness": 4.507347106933594, "identity": 0.20131248235702515, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/0a82748e2d7d1dcd70d85f3da709c0725beb537590b7941a8aca492ef63e77f2.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "0b2995a78e62658cfe3b4765047dda45d75b909ffecebe31a842f5fed78f1b9c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "07b6cdc725766f2bace67bb7f5b9610d25f0785fad8af39a2e645dea9a1ee3c2", "generation_seconds_batch": 25.52321206103079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7585267424583435, "target_z": 0.30859373595459993, "ce": 5.43088436126709, "genuineness": 4.570107460021973, "identity": 0.7141153216362, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/0b2995a78e62658cfe3b4765047dda45d75b909ffecebe31a842f5fed78f1b9c.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "0b955cbb3cddadbd92fabaf083e7417ab803849d2e42e48e37917ae185eb90cf", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fe23bde89015fecef5e48c3b550307fc4f495b9dbaa1e855ec544c0d0db615a0", "generation_seconds_batch": 25.133542594034225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20831269025802612, "target_z": -0.26367188928756213, "ce": 5.974957466125488, "genuineness": 4.758388519287109, "identity": 0.7640408277511597, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/0b955cbb3cddadbd92fabaf083e7417ab803849d2e42e48e37917ae185eb90cf.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "0be86f51d54a906dd6a32738851e227832303b1987749d48998ed9e758f65378", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fd313cdca36c12d391cab73f42076d161690b7a7627421a4400b868bb8e82a93", "generation_seconds_batch": 26.96549383806996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27216005325317383, "target_z": -0.19726564074053454, "ce": 5.998785495758057, "genuineness": 4.6705241203308105, "identity": 0.5219892263412476, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/0be86f51d54a906dd6a32738851e227832303b1987749d48998ed9e758f65378.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "44bd125f1760924e74437fdb03586ded72872e172da5edc028b942d5fc8b4bcf", "generation_seconds_batch": 19.330069506075233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2590150237083435, "target_z": -0.21093749903135173, "ce": 6.157639026641846, "genuineness": 4.507347106933594, "identity": 0.8161264061927795, "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_Emotional_Numbness/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "0de1bbb080a25750133cbc4ed903e196f8c807063f4da03699d992db0fd79453", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "de815b2d396a6cb7e1f5184b52f1195be37905e31c1b681580bb352c00dc5215", "generation_seconds_batch": 26.050170053029433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6158090829849243, "target_z": 0.1601562136756895, "ce": 5.855817794799805, "genuineness": 4.432034492492676, "identity": 0.5663301944732666, "hypothesis": "Ik 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_Emotional_Numbness/0de1bbb080a25750133cbc4ed903e196f8c807063f4da03699d992db0fd79453.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "0df22d6d85190b76ee2b0ad6bb40bd785668e16cfefb58dcc2d116edb23e0629", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c9ee6f037f64d654dbf4cc0f9cb9967af3a85e847f357413b874becf60bdbc5", "generation_seconds_batch": 25.18769460101612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5754350423812866, "target_z": 0.11816405535621893, "ce": 5.7128496170043945, "genuineness": 4.6956281661987305, "identity": 0.42605602741241455, "hypothesis": "Ik 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_Emotional_Numbness/0df22d6d85190b76ee2b0ad6bb40bd785668e16cfefb58dcc2d116edb23e0629.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "0edcc358770394407e7e98f33045308df8d7688e9e518e53a81bf17801e4b920", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "94fc8615477e634f6039534e35570ea1950e09e00e8343b110f852be76c759aa", "generation_seconds_batch": 22.707526679965667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2608928680419922, "target_z": -0.20898439413080352, "ce": 5.998785495758057, "genuineness": 4.65797233581543, "identity": 0.7919773459434509, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/0edcc358770394407e7e98f33045308df8d7688e9e518e53a81bf17801e4b920.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "0f06db546f4a1ecea2b551fffb70067b0940046b76e19be3ac0a3fde639d9a85", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fa4b3ea1e23adb030672ca7c7b3c0aaeb19ba98187729b969cc5bdd0bfca8f23", "generation_seconds_batch": 27.293133305036463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16136610507965088, "target_z": -0.31250000774918624, "ce": 6.213237762451172, "genuineness": 4.632867813110352, "identity": 0.5449106693267822, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/0f06db546f4a1ecea2b551fffb70067b0940046b76e19be3ac0a3fde639d9a85.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "0f9abb787c65c6a921ab7466aa44e71d596a1898559cfbff990afed6a9387d63", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "725c2c5beec4f0fc1e3e3817f310202b1e1d704bd7f8be26ef782260c2e600c5", "generation_seconds_batch": 23.3287451940123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38764870166778564, "target_z": -0.0771484184902775, "ce": 6.0146708488464355, "genuineness": 4.7834930419921875, "identity": 0.31557750701904297, "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_Emotional_Numbness/0f9abb787c65c6a921ab7466aa44e71d596a1898559cfbff990afed6a9387d63.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "1032ebd9f30e6091307b88036558ed9f15336237bb8189b8118215ffd2eb3ea7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "df1670dc418ecd544e4bd16ab6dc6f93ecb36e4c5e139711d269b02a3df00037", "generation_seconds_batch": 16.96773057000246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10690805315971375, "target_z": -0.369140638803238, "ce": 6.141753673553467, "genuineness": 3.6914620399475098, "identity": 0.3185773193836212, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1032ebd9f30e6091307b88036558ed9f15336237bb8189b8118215ffd2eb3ea7.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "1039a687e0b4589da3aaed179effa47f1dc7ce45c6433b68eb0e3f203937ffad", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7bde0ad70a05a595b4954b8c19805cc5311f40bc56f4749a321d08ed37132cc4", "generation_seconds_batch": 23.099654358928092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6524274349212646, "target_z": 0.19824216219406368, "ce": 5.5738525390625, "genuineness": 4.507347106933594, "identity": 0.661436140537262, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1039a687e0b4589da3aaed179effa47f1dc7ce45c6433b68eb0e3f203937ffad.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "1045147d24e36ebef94228fd6046dc642b7a5c99d75d1db60f169ad8dd1f7c29", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9bbf2bcbd5a992b3133eb490083226857126847df121e467f5387484dbc9b2ad", "generation_seconds_batch": 24.35756873898208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07874011993408203, "target_z": -0.3984374912821655, "ce": 6.340320587158203, "genuineness": 4.406930446624756, "identity": 0.5700343251228333, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1045147d24e36ebef94228fd6046dc642b7a5c99d75d1db60f169ad8dd1f7c29.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "1087ba2f66e869afd4d78820063a2bc23ae08a375dd164199179bfe24b964f61", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d477f54b529c94df54c9eba7fdd38bf31a340c478e87d82e3443513627e4518b", "generation_seconds_batch": 26.818048786954023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1463432013988495, "target_z": -0.32812500193729655, "ce": 6.141753673553467, "genuineness": 4.507347106933594, "identity": 0.530960202217102, "hypothesis": "De deur 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_Emotional_Numbness/1087ba2f66e869afd4d78820063a2bc23ae08a375dd164199179bfe24b964f61.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "10da5a4b68acaaf522e54c9c761aa29389212e028a9b884ac62bf4d7bc2d48de", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "60057eafcd9afa000ee252b811433d88a87116cd48c65357af04d749f91aebc3", "generation_seconds_batch": 20.00443698395975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36980897188186646, "target_z": -0.09570313202270003, "ce": 5.863759994506836, "genuineness": 4.419482707977295, "identity": 0.6092857122421265, "hypothesis": "Ik 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_Emotional_Numbness/10da5a4b68acaaf522e54c9c761aa29389212e028a9b884ac62bf4d7bc2d48de.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "10f7907a0d3f35b4ecfb6b8a366d122d9d116ac1a8549cf6050c283cf4aa825c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fa7d2cf0a8bacfbed37864133fedf4df9c3be981eab0605ac7c97b7098366e1", "generation_seconds_batch": 25.416390910046175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7078244686126709, "target_z": 0.2558594076918795, "ce": 5.6532793045043945, "genuineness": 4.356721878051758, "identity": 0.4178485870361328, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/10f7907a0d3f35b4ecfb6b8a366d122d9d116ac1a8549cf6050c283cf4aa825c.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "118a3b51b6d046bb3910db9250b4937f5203d18aa62a083de5bf54b06c455e86", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b51aeaf71f3709060a05246a6c36edfe4cdeed243445d14ab6ef6337e24f9c5b", "generation_seconds_batch": 26.15057247201912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7491374015808105, "target_z": 0.29882808746487916, "ce": 5.8875885009765625, "genuineness": 4.808597087860107, "identity": 0.7252256870269775, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/118a3b51b6d046bb3910db9250b4937f5203d18aa62a083de5bf54b06c455e86.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "11a9378946ce535615387ebc039eab404d4557a4400de45e072e323bd3994107", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a9c184ac11008eae592507540df19e68269b8c4940e45c41eb504a2de935e6c9", "generation_seconds_batch": 24.89188087102957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2101905643939972, "target_z": -0.26171875339026895, "ce": 6.252951145172119, "genuineness": 4.457139015197754, "identity": 0.6421324014663696, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/11a9378946ce535615387ebc039eab404d4557a4400de45e072e323bd3994107.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "11e077e9faf4ced778fa30a8fd547b61cdef9af5e6411d7e8560183b3eae493a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "92fea572df3d8258fc14fa6177a662dd68a506101f62bd1bca850c96d9d46d75", "generation_seconds_batch": 24.819998366991058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3576028645038605, "target_z": -0.1083984378632431, "ce": 5.982900142669678, "genuineness": 4.570107460021973, "identity": 0.5185463428497314, "hypothesis": "De deur 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_Emotional_Numbness/11e077e9faf4ced778fa30a8fd547b61cdef9af5e6411d7e8560183b3eae493a.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "128e1eeede44e797eed2c59f8adb3d21ba35e42e3d196e01de451284e0f72573", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "191edd9c9a88da885339c0abe7efae6f9b6068aca997eec0ebb6c29d03aa1368", "generation_seconds_batch": 24.43625410401728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23460279405117035, "target_z": -0.23632812621081034, "ce": 5.696964263916016, "genuineness": 4.2751336097717285, "identity": 0.4415295720100403, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/128e1eeede44e797eed2c59f8adb3d21ba35e42e3d196e01de451284e0f72573.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "752c8719ecd49a9746bfccff62f843629d57f0cee530761349b410b2a05acfd7", "generation_seconds_batch": 19.828906620037742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09000730514526367, "target_z": -0.3867187378918965, "ce": 6.165581703186035, "genuineness": 4.413206577301025, "identity": 0.7220292091369629, "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_Emotional_Numbness/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.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": "12fa9dd1c4dc2c9fe4091e4a80b424d9504f0fbcc53d79295dd450830967df60", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4086e677ec60e2c86902a2df6b50ded1d0b4e246bcb6c169f462d828a73d1cce", "generation_seconds_batch": 22.392635217984207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5604121685028076, "target_z": 0.10253909216485359, "ce": 5.593709468841553, "genuineness": 4.6956281661987305, "identity": 0.870329737663269, "hypothesis": "Seine Nachricht kam, als sie schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.08333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/12fa9dd1c4dc2c9fe4091e4a80b424d9504f0fbcc53d79295dd450830967df60.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": "13544070aa31a24763c162c489b1c38bedea21983f0ae26b144ce80f4f829ca9", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "160f152f8996f6348d7231c71beeaa6b29ba71fb1b73f53b10d2e65030629111", "generation_seconds_batch": 24.845724854967557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1002979278564453, "target_z": 0.6640624854702758, "ce": 5.414999485015869, "genuineness": 4.582659721374512, "identity": 0.6512094736099243, "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_Emotional_Numbness/13544070aa31a24763c162c489b1c38bedea21983f0ae26b144ce80f4f829ca9.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "136fa8f0efbe4221dcf4443f31caf11368eb18e44f4186c647717a5974f8a6e5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4c179dcc734b7d115f53c63ca2eb4d1aba2408c645d33a3268dc7f4aeca0ec6c", "generation_seconds_batch": 23.205603576032445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.414877712726593, "target_z": -0.04882811846162411, "ce": 5.824047088623047, "genuineness": 4.946669578552246, "identity": 0.6893314123153687, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/136fa8f0efbe4221dcf4443f31caf11368eb18e44f4186c647717a5974f8a6e5.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "13bb6233568964bdb886c9625a4b3b24700053887963975612c7580766beafc6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a413885812cd2d8be664d9104ccbd7ed98f0c584290c9b26f023951b49c72c0d", "generation_seconds_batch": 24.32474495691713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09751874208450317, "target_z": -0.37890625629621383, "ce": 6.419747352600098, "genuineness": 4.7081804275512695, "identity": 0.23824414610862732, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/13bb6233568964bdb886c9625a4b3b24700053887963975612c7580766beafc6.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "14540df23cf795ea8078562cc4ab05c9dd7e9048500477235def380f66567f02", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bf9066dcb971100816e50b5dc417a085a790471ab2f1cc6ce0393ba48dd66e4c", "generation_seconds_batch": 26.40845945291221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15761038661003113, "target_z": -0.3164062485470276, "ce": 6.221180438995361, "genuineness": 4.482243061065674, "identity": 0.3561808466911316, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/14540df23cf795ea8078562cc4ab05c9dd7e9048500477235def380f66567f02.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": "14c7ca78e3a313bbeed57a86c124a8a469bb4c9442b0d9b425350897a3cd252d", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46d53fcb387f3c49ee0396f288107bb8b3187839c16131035f5a8993561dc184", "generation_seconds_batch": 17.10462384391576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6514885425567627, "target_z": 0.19726564074053454, "ce": 5.585766792297363, "genuineness": 4.7332844734191895, "identity": 0.8119242787361145, "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_Emotional_Numbness/14c7ca78e3a313bbeed57a86c124a8a469bb4c9442b0d9b425350897a3cd252d.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "14dcb3e6850fe4fcdacb5973500027eefb7affd7aaf8fe3e424ef3d61f884095", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0adcb81608915dcd82d714773ed73b62d19f04d449bf74dba7b1a4cf7a1ab2e4", "generation_seconds_batch": 24.841172161977738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.245869979262352, "target_z": -0.22460937282054136, "ce": 6.054384231567383, "genuineness": 4.507347106933594, "identity": 0.6642365455627441, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen het er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/14dcb3e6850fe4fcdacb5973500027eefb7affd7aaf8fe3e424ef3d61f884095.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "14eabb3306a8e145b973969f1a61a0844d3b1c030c77fa2474951684910e3b98", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5cb6141d166f00bcf7cf36dad5d6786eae22c6578d12d23cd71b92ff17b01fce", "generation_seconds_batch": 24.66542209708132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19328978657722473, "target_z": -0.27929688347567244, "ce": 6.070269584655762, "genuineness": 4.444586753845215, "identity": 0.5496828556060791, "hypothesis": "Ik 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_Emotional_Numbness/14eabb3306a8e145b973969f1a61a0844d3b1c030c77fa2474951684910e3b98.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "46d0cb68d87fe39f4f81295e601cfd192cf79d98a5f7ffbfff688f7878081f40", "generation_seconds_batch": 18.838446403038688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43694260716438293, "target_z": -0.025878903404595678, "ce": 6.395919322967529, "genuineness": 4.7332844734191895, "identity": 0.5166343450546265, "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_Emotional_Numbness/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "1558ac13d860a8775f330592c1a96bc354ae77cbb8afbdc695ce78577c58a44d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fa053cba90477555237323035a698efa23f39c408aeb6a5a9219e1b40c7efb8f", "generation_seconds_batch": 25.633277017972432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18390047550201416, "target_z": -0.2890625009686483, "ce": 6.046441555023193, "genuineness": 4.482243061065674, "identity": 0.5507110357284546, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1558ac13d860a8775f330592c1a96bc354ae77cbb8afbdc695ce78577c58a44d.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "155f26b8c65a1285f92c9616e949d90120cb0fb125d859d558a5ed5de92cfbaa", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "20214f23130403f5fea70a0c4ce2bcff3f927110f9f36acc54f0b21fcb8d4fc9", "generation_seconds_batch": 26.623387007974088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7942061424255371, "target_z": 0.3457031010259551, "ce": 5.681078910827637, "genuineness": 4.758388519287109, "identity": 0.7636650204658508, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/155f26b8c65a1285f92c9616e949d90120cb0fb125d859d558a5ed5de92cfbaa.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "1571fab733736cbdd7ef8e5a88f4d5a231861675aff363aeaed76ccd4686e7aa", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c1c500275f803dca449f1f5aafe423572a9f695b40a4b22d208eaaa4a4af943f", "generation_seconds_batch": 25.49756037502084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5989083647727966, "target_z": 0.14257814558377596, "ce": 6.173524379730225, "genuineness": 4.758388519287109, "identity": 0.665104329586029, "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_Emotional_Numbness/1571fab733736cbdd7ef8e5a88f4d5a231861675aff363aeaed76ccd4686e7aa.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "1640d996c066596d3ae37af34bbd6b054f5fff5154bc6779a346de579a48f4e6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "984997ba2a84ac53ada14f4c435d1938de9e12b2a08882daf03d9f88d5074739", "generation_seconds_batch": 25.087426787940785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2411753237247467, "target_z": -0.22949218156702927, "ce": 5.772419452667236, "genuineness": 4.444586753845215, "identity": 0.7353387475013733, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuando 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_Emotional_Numbness/1640d996c066596d3ae37af34bbd6b054f5fff5154bc6779a346de579a48f4e6.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "1669a683e29dbe86444954656756aa669984a484d1bc4c0a259e197098d3bcf9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "969b28e4a1966ef808e4905f254990b8dc69cd8936340cc9716ddc32abfc888f", "generation_seconds_batch": 26.818048786954023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3599501848220825, "target_z": -0.1059570412391854, "ce": 6.022613525390625, "genuineness": 4.545003414154053, "identity": 0.6219083666801453, "hypothesis": "De deur 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_Emotional_Numbness/1669a683e29dbe86444954656756aa669984a484d1bc4c0a259e197098d3bcf9.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "169048c246d82d89f99bda9a52a21c3a3cde7c31f12b79ba0e7c900db746e474", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "875b1a5831b3c33afb8bdb2d99c5c7d7330ddbb9b5f678b2c593ca45804ca1fa", "generation_seconds_batch": 22.295547902002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2693432569503784, "target_z": -0.2001953290881018, "ce": 6.229123115539551, "genuineness": 4.7081804275512695, "identity": 0.5875228047370911, "hypothesis": "La porte t'est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/169048c246d82d89f99bda9a52a21c3a3cde7c31f12b79ba0e7c900db746e474.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "169e18db2155797a4459e9b2a2e65697aba06e41c1357a30ad2174fbeb46cab0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e7f628ab902545133a749984a51d17fcebb0a80c9ed3b246e93e48631c0d4ec", "generation_seconds_batch": 18.2757614570437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6777786016464233, "target_z": 0.22460935732216888, "ce": 5.772419452667236, "genuineness": 4.645420074462891, "identity": 0.5652648210525513, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/169e18db2155797a4459e9b2a2e65697aba06e41c1357a30ad2174fbeb46cab0.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "17156958942f06f81b4146b33dfad5b650648c5640a7fcd91e57d5969b30541f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "aeb919c0b7d2134a5906c86452a43bb994ade846b45de88839f43bcdfc2f29ff", "generation_seconds_batch": 25.86902217392344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14446532726287842, "target_z": -0.3300781378345897, "ce": 6.0146708488464355, "genuineness": 4.425758361816406, "identity": 0.7538048624992371, "hypothesis": "Ik 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_Emotional_Numbness/17156958942f06f81b4146b33dfad5b650648c5640a7fcd91e57d5969b30541f.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "1716b0c6469e4d5f7b3cdb012710fb682e9bc0d88aac47aa800573f235c43dbd", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cc19958c925b5feb30a57d78f6335c2fb75670244e9d0ea9b6f824a8299ef13a", "generation_seconds_batch": 24.534473272040486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3350684940814972, "target_z": -0.13183594464378107, "ce": 6.046441555023193, "genuineness": 4.645420074462891, "identity": 0.7116509675979614, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1716b0c6469e4d5f7b3cdb012710fb682e9bc0d88aac47aa800573f235c43dbd.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "1858ed3994466fe82ceadfda2c95803a8cbf9d2fdcafeb6d48df41a7a5e3b062", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7c880c19a36a51e73e1d355378a6fcbf030509e7a95dbb18aa200e0ed14c239f", "generation_seconds_batch": 24.17088040302042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14070960879325867, "target_z": -0.3339843786324311, "ce": 6.0146708488464355, "genuineness": 4.6705241203308105, "identity": 0.7786626815795898, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1858ed3994466fe82ceadfda2c95803a8cbf9d2fdcafeb6d48df41a7a5e3b062.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": "194f6c54f18f66ed2a391ccd55d693b3486f4e0ee466cfa81cd0dd05dab43d61", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "5109847a11cb5d9551e4c0f1a2a4733bfe91dc2f75a9511a6631da663d0f40a5", "generation_seconds_batch": 18.43436354806181, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6712061166763306, "target_z": 0.21777345917350527, "ce": 5.855817794799805, "genuineness": 4.833701133728027, "identity": 0.6908267736434937, "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_Emotional_Numbness/194f6c54f18f66ed2a391ccd55d693b3486f4e0ee466cfa81cd0dd05dab43d61.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": "1973018b005fb9b02f61f543901daaf2838b0eacb2ad52294da7f33bbd6dab2f", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "acd91fdf4983515dcc996a509ffcb6f5fd4f300dc4e52389fbef8de3cf2916c2", "generation_seconds_batch": 24.556372502003796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3820151090621948, "target_z": -0.08300779518541199, "ce": 5.784333229064941, "genuineness": 4.720732688903809, "identity": 0.8777841329574585, "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_Emotional_Numbness/1973018b005fb9b02f61f543901daaf2838b0eacb2ad52294da7f33bbd6dab2f.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "19bed32fee2399affdc99940c8f49fccd77ee0cfb3b160ca1cb97c60898e7099", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ae75c17c1ee544af4cd7d716080d6af253c38710a8e5f6d4f5a1fe919e9cd2df", "generation_seconds_batch": 18.540569615084678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6627557277679443, "target_z": 0.20898439413080352, "ce": 5.736677646636963, "genuineness": 4.507347106933594, "identity": 0.736608624458313, "hypothesis": "De deur 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_Emotional_Numbness/19bed32fee2399affdc99940c8f49fccd77ee0cfb3b160ca1cb97c60898e7099.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": "19df3bb5d3ab0b689721e2a9076cbd51b4d01732bdbd85f1ecb2329e277e4d72", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Escribí el número en el sobre.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "aaefc1cc66b1258e677cc1cec43ecf3fef81b7cb5dedf9b287f6f8d2d1f2405b", "generation_seconds_batch": 16.9954869489884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42755329608917236, "target_z": -0.0356445208975715, "ce": 5.71682071685791, "genuineness": 4.7081804275512695, "identity": 0.7278525829315186, "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_Emotional_Numbness/19df3bb5d3ab0b689721e2a9076cbd51b4d01732bdbd85f1ecb2329e277e4d72.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "1a571d8497bb8dc0ce72aafb01f9d58318307f32530df57ad193b70ed4b594e3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "34018596c66cc262c76e496643a278848eaf23048b1eab1a928da21e27518fc3", "generation_seconds_batch": 18.165423641097732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1951676607131958, "target_z": -0.2773437475783793, "ce": 6.1020402908325195, "genuineness": 4.833701133728027, "identity": 0.6543546319007874, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1a571d8497bb8dc0ce72aafb01f9d58318307f32530df57ad193b70ed4b594e3.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "1ba9179a0b27c91b899074af7bc6b2947d34f317d14f380aadbc44c565679439", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "766a49de9a5f21452309a4a8e70a8edce4897ae6e5038a72371ca7b46c24a715", "generation_seconds_batch": 23.601214546943083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17826688289642334, "target_z": -0.29492187766378275, "ce": 5.911416053771973, "genuineness": 4.362998008728027, "identity": 0.5712321996688843, "hypothesis": "Ik 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_Emotional_Numbness/1ba9179a0b27c91b899074af7bc6b2947d34f317d14f380aadbc44c565679439.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "1cb73b42d942c176fe4312b6e6c29e0bae3db79047d8bfdf6e82a49ecd7b73a3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e0992c2f7c60aeae26aef25fa9f79a51130023b0883ea887b8cb92a823802c53", "generation_seconds_batch": 15.423867790959775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29845017194747925, "target_z": -0.16992186216541028, "ce": 6.268836498260498, "genuineness": 4.6705241203308105, "identity": 0.4375728964805603, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1cb73b42d942c176fe4312b6e6c29e0bae3db79047d8bfdf6e82a49ecd7b73a3.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "561080cb6629059c2aa7f0f16a0fdcc831d8dbd27cca746d7355aa0b8b60a0d4", "generation_seconds_batch": 19.166587560088374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05057215690612793, "target_z": -0.42773437475783793, "ce": 6.260893821716309, "genuineness": 4.306513786315918, "identity": 0.711740255355835, "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_Emotional_Numbness/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "a8632db790384c39baee8a1bd858f2f59df16aacd16b8421741afccf7ede5ffe", "generation_seconds_batch": 17.36467011703644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09000730514526367, "target_z": -0.3867187378918965, "ce": 6.395919322967529, "genuineness": 4.494794845581055, "identity": 0.6078379154205322, "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_Emotional_Numbness/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.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": "1d95a1bcb1b8759e254e980ccebbf0f9a8882f15df9650c55fd0bb726311b9da", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ac2d932af43654b20f755f01b825764b326819c2f008f724c7b6a125257cd7f9", "generation_seconds_batch": 26.114921011961997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4767298400402069, "target_z": 0.015502929006419178, "ce": 5.7406487464904785, "genuineness": 4.7332844734191895, "identity": 0.7779262661933899, "hypothesis": "Les clés sont sur la table de la cuisine, j'ai regardé dans le tiroir, puis près de la fenêtre prends les cons, tu partiras.", "wer": 0.041666666666666664, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1d95a1bcb1b8759e254e980ccebbf0f9a8882f15df9650c55fd0bb726311b9da.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "1db4ee411b82fb777c63401e01501a876a733667e8d1581345c065c603769649", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4be50efadf6a666f911dcb3161bcf36c26f814c41cf9c5a6bed9da95344afe91", "generation_seconds_batch": 15.808669785037637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27216005325317383, "target_z": -0.19726564074053454, "ce": 5.982900142669678, "genuineness": 4.469690799713135, "identity": 0.3815341293811798, "hypothesis": "De deur 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_Emotional_Numbness/1db4ee411b82fb777c63401e01501a876a733667e8d1581345c065c603769649.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "1dc6107bb42ba70d94ca275b80b5599d85103cb743dc671b35a4ada36f2d73c3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fc17d8a2e0da51dc1c0512ac9a7ef605c9efd07970d0a20da8e6a9df5c40edb4", "generation_seconds_batch": 23.200971873942763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 6.324435234069824, "genuineness": 4.369274139404297, "identity": 0.3054404854774475, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1dc6107bb42ba70d94ca275b80b5599d85103cb743dc671b35a4ada36f2d73c3.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "1e38f3ebbdb72115d99d626cd61d696efbf495ca8bae4dd9458fd0a5d2639859", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c45ae5afc3a7fb77befeb3df62dd4213b97e0fc030fd7d8dda02bf4aeaf09f5c", "generation_seconds_batch": 18.51054581697099, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.266526460647583, "target_z": -0.20312501743566905, "ce": 6.054384231567383, "genuineness": 4.457139015197754, "identity": 0.6441583633422852, "hypothesis": "De deur 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_Emotional_Numbness/1e38f3ebbdb72115d99d626cd61d696efbf495ca8bae4dd9458fd0a5d2639859.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "1e46f83ec2e1e528fb58e206976f51f733cf4df21d029f5d7e8e2b5cb279447c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "69e02886c8be6ef65e6f0a0684edb4b59b252ef0b245975d37d004124643bcb5", "generation_seconds_batch": 27.13431357999798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45642542839050293, "target_z": -0.00561524633175221, "ce": 6.125868320465088, "genuineness": 4.607763767242432, "identity": 0.7815158367156982, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1e46f83ec2e1e528fb58e206976f51f733cf4df21d029f5d7e8e2b5cb279447c.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "1e6035a2662d451a0f328d665ab15049b5018b9e60fb695255a7c55ce3703197", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3c2f4999e28cfb1fe878a04fd9e419107f03b921b2c0828ff71a0067668b23b0", "generation_seconds_batch": 18.92763454897795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06183934211730957, "target_z": -0.4160156213675689, "ce": 6.205295085906982, "genuineness": 4.770940780639648, "identity": 0.5367110371589661, "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_Emotional_Numbness/1e6035a2662d451a0f328d665ab15049b5018b9e60fb695255a7c55ce3703197.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "1e632f9c8ca7f4ffb7d431c182ff36795ce037deea5556ce5c83b2d24e1f6fe4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8c26cd82cf39beb244f2322d3e14d466c0b9ec9963a95bde24d5c31a35666023", "generation_seconds_batch": 24.726480326033197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7453817129135132, "target_z": 0.29492187766378275, "ce": 5.569881439208984, "genuineness": 4.507347106933594, "identity": 0.8281071186065674, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/1e632f9c8ca7f4ffb7d431c182ff36795ce037deea5556ce5c83b2d24e1f6fe4.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "1e6d1584d5baf503bfc8223c0955ac65385159c9660de0f3e7b3b1a6db0487de", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca3f38dd8f995fd79723f7b0addaf87e4406a2205894821e4d7b1dee36708707", "generation_seconds_batch": 25.664538023993373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2618318200111389, "target_z": -0.20800781068378446, "ce": 5.998785495758057, "genuineness": 4.770940780639648, "identity": 0.7851365208625793, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/1e6d1584d5baf503bfc8223c0955ac65385159c9660de0f3e7b3b1a6db0487de.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "1e73ad6d8bf462933321a710ba57c8ddf7da32377bd88c74f35403cbfb3f4a39", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f95ce5a8ca5c4d0dad88ceb86ad8755b1d9a0fc988a9a6caeb74d7cd2097fabc", "generation_seconds_batch": 22.61510144593194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10127449035644531, "target_z": -0.3749999845016275, "ce": 6.157639026641846, "genuineness": 3.8044304847717285, "identity": 0.25380513072013855, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1e73ad6d8bf462933321a710ba57c8ddf7da32377bd88c74f35403cbfb3f4a39.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "1e9f83b1c759d399f27c4624b0e4c4c56eb2e6ff92e03b1c46c322a488210543", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f9ed64835e8630ddfa4c0dacd6e214faede6790f28a0f27b5d76565101cae891", "generation_seconds_batch": 22.9121555009624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1801447570323944, "target_z": -0.2929687417664896, "ce": 6.054384231567383, "genuineness": 4.7332844734191895, "identity": 0.7069967985153198, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1e9f83b1c759d399f27c4624b0e4c4c56eb2e6ff92e03b1c46c322a488210543.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "5e52081c222fdcd614953c5393e8788c1ee3cf45e5bc9a9c0f5182cec8f55807", "generation_seconds_batch": 19.166587560088374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06183934211730957, "target_z": -0.4160156213675689, "ce": 6.038498878479004, "genuineness": 4.105680465698242, "identity": 0.7547096610069275, "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_Emotional_Numbness/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "1ec913ee1704ad9868217662bf02467c7f243aaf604e218c7a6365a448a42771", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f92ad1842876ff89a624470692c46666f7fbb22d472bb4a7ec88e58b334d305", "generation_seconds_batch": 18.51054581697099, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12944242358207703, "target_z": -0.34570313202270003, "ce": 6.1020402908325195, "genuineness": 4.344170093536377, "identity": 0.705132246017456, "hypothesis": "De deur 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_Emotional_Numbness/1ec913ee1704ad9868217662bf02467c7f243aaf604e218c7a6365a448a42771.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "1f1752130643e470f1febee1758a2b9d4d9a6eb7c2968dc9caef2d4790f416c9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0e461b752b6fa74c1467492baf7cf3abe9696a3bac32e3e6c104e6f34ee4b482", "generation_seconds_batch": 26.049036048934795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4558386206626892, "target_z": -0.006225572240207911, "ce": 5.8875885009765625, "genuineness": 4.557555198669434, "identity": 0.6949899196624756, "hypothesis": "La porte 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_Emotional_Numbness/1f1752130643e470f1febee1758a2b9d4d9a6eb7c2968dc9caef2d4790f416c9.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "1f667a7688b730c84a41476864b4804a75c695b53ede87182f92981cd9b8e7d4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "532edd35d8789369b4eaba46b577d3104180a1ac0eec8cef9883cb2ba9301a2d", "generation_seconds_batch": 25.65599920495879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09188514947891235, "target_z": -0.3847656329913483, "ce": 6.141753673553467, "genuineness": 3.961331605911255, "identity": 0.15413126349449158, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/1f667a7688b730c84a41476864b4804a75c695b53ede87182f92981cd9b8e7d4.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "1fca095dadbbd0eff81763796f368d0ca2257aed1cb85e51f225110f86e8e31a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e344ee7c923bec44dfce7bf4687189dc7fa670702525db5c39bfbbbe9ca81579", "generation_seconds_batch": 25.86902217392344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24305318295955658, "target_z": -0.22753906116810863, "ce": 6.062326908111572, "genuineness": 4.319066047668457, "identity": 0.5622738599777222, "hypothesis": "Ik 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_Emotional_Numbness/1fca095dadbbd0eff81763796f368d0ca2257aed1cb85e51f225110f86e8e31a.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": "1fd77f36f7788d359473d3c7e522d1298d2a2a4ddcdea5cad271255dc2143a67", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I wrote the number on the envelope.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6b3c1fe8b6a091872e5fe5549be8ac249bfbd5df9f10065ad4e94b1eba8061e6", "generation_seconds_batch": 21.882813064032234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4513786733150482, "target_z": -0.01086426612168603, "ce": 6.213237762451172, "genuineness": 4.557555198669434, "identity": 0.3807874321937561, "hypothesis": "I wrote the number on the envelope. I'll 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_Emotional_Numbness/1fd77f36f7788d359473d3c7e522d1298d2a2a4ddcdea5cad271255dc2143a67.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "1fde656705cd3850f8042890d920baa292fa1519eda40ba0584e87b3300ad406", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a4fe57787700e0ab82879b32851c522448d48d5e722a22ca645e039da28510cc", "generation_seconds_batch": 24.520811351016164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.735992431640625, "target_z": 0.2851562911675519, "ce": 6.022613525390625, "genuineness": 4.833701133728027, "identity": 0.7955458164215088, "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_Emotional_Numbness/1fde656705cd3850f8042890d920baa292fa1519eda40ba0584e87b3300ad406.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "2006b8b983b641a893265d4e82cde11a9d61943865f35ba039b828047aa739e8", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "980a3be73902769d8643037e1a5651c98879033422b9f6a8498d85668bb5318f", "generation_seconds_batch": 19.937948689912446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5061888098716736, "target_z": 0.04614256047743914, "ce": 6.022613525390625, "genuineness": 4.457139015197754, "identity": 0.6304872035980225, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2006b8b983b641a893265d4e82cde11a9d61943865f35ba039b828047aa739e8.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "2079355cc4e4b14a774763513f55d3f192ea58891dbc2cfa41c9fc6b88570c92", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b0d762540a12eaaf8b9c52cb23e7d64e3f98ec3cec5292c93b322ed296656fa9", "generation_seconds_batch": 23.200971873942763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13507601618766785, "target_z": -0.33984375532756556, "ce": 6.1894097328186035, "genuineness": 4.381826400756836, "identity": 0.34564918279647827, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2079355cc4e4b14a774763513f55d3f192ea58891dbc2cfa41c9fc6b88570c92.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "21334f8a480cf400561b86747a75ce18cb507786680f82f5dcd8771b3e918d84", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d8ebc4a7848c3174eecc8c5cb7ed8ec6bd914f1ddc6ace8d164c879572a1094c", "generation_seconds_batch": 19.30635125900153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10127449035644531, "target_z": -0.3749999845016275, "ce": 6.133810997009277, "genuineness": 4.432034492492676, "identity": 0.34320729970932007, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/21334f8a480cf400561b86747a75ce18cb507786680f82f5dcd8771b3e918d84.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "2169e4e79defdee314625d15841c257f5c4ed7e0a5c307c678c717379e844632", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b4385192ff6a72122f9fc55a3281218cffca07529b4e9f8bcffa78da9afbd823", "generation_seconds_batch": 23.524446388939396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09376302361488342, "target_z": -0.3828124970940552, "ce": 5.9431867599487305, "genuineness": 4.3881025314331055, "identity": 0.7191023826599121, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/2169e4e79defdee314625d15841c257f5c4ed7e0a5c307c678c717379e844632.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "219029911cc626b95faf068f04e08a9beffacada1ccf0fe204266566407581b6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fa2d5ba6f924d40e8a7eee9eef2f7f1919980f43e9b4a0b6244f0d12f99b83d2", "generation_seconds_batch": 23.099654358928092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38295403122901917, "target_z": -0.0820312427351379, "ce": 5.816103935241699, "genuineness": 4.15588903427124, "identity": 0.4450412392616272, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/219029911cc626b95faf068f04e08a9beffacada1ccf0fe204266566407581b6.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": "21b39a144e8040f7354248947ee4a1aba60605af0aeb58cf2958bf9faf7d6b62", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "c602f2819dc80aad7037de256b016df06ec5b1addc3b4c8a59783cf60add01ea", "generation_seconds_batch": 17.592817803029902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46816208958625793, "target_z": 0.006591798782026302, "ce": 6.1020402908325195, "genuineness": 4.7081804275512695, "identity": 0.8363628387451172, "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_Emotional_Numbness/21b39a144e8040f7354248947ee4a1aba60605af0aeb58cf2958bf9faf7d6b62.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "22a11b7b3374bcb458274f41e5d518f8f2bac4d757bdc700350b6c8da847cc8e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f00c60c8b1e740d8860daa76ee585da12939c6f9808ef8238a151ef68e02c506", "generation_seconds_batch": 23.924712667940184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21394629776477814, "target_z": -0.2578124970940552, "ce": 6.340320587158203, "genuineness": 4.469690799713135, "identity": 0.5737366676330566, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/22a11b7b3374bcb458274f41e5d518f8f2bac4d757bdc700350b6c8da847cc8e.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": "22edf45b3ad1a10e7717869865094d536d3324b8127024d99fd02c92e0d8e23c", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Escribí el número en el sobre.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e4387cc1581ec947a466d1886d197744d60099bb504a7dc4d499003088315c2c", "generation_seconds_batch": 22.009171106037684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29375550150871277, "target_z": -0.1748046864102707, "ce": 5.542081832885742, "genuineness": 4.68307638168335, "identity": 0.5867279767990112, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámeme cuando tengas un momento.", "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_Emotional_Numbness/22edf45b3ad1a10e7717869865094d536d3324b8127024d99fd02c92e0d8e23c.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "23edd58ce2499baca3c94e8c694bc374ce99dbfea3823aeea0ec6d84e5720fc5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fccf581afcf586434fd913124614732b1a2b6c32ac0d7aef546d428704ef73ff", "generation_seconds_batch": 16.96773057000246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06935077905654907, "target_z": -0.40820313977188627, "ce": 6.252951145172119, "genuineness": 4.2751336097717285, "identity": 0.16101498901844025, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/23edd58ce2499baca3c94e8c694bc374ce99dbfea3823aeea0ec6d84e5720fc5.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "241fb8a25e1039f118eba5324e22d1ba42013603253c6eafe3e14aad9fb7c32e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4d163acf3d3b61718b1cd5629cd9f031b84b889381424a44d2c9dffd249b4e05", "generation_seconds_batch": 19.756263675983064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09564089775085449, "target_z": -0.380859361196762, "ce": 6.213237762451172, "genuineness": 4.369274139404297, "identity": 0.3568460941314697, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/241fb8a25e1039f118eba5324e22d1ba42013603253c6eafe3e14aad9fb7c32e.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "2473427ee93e8f8a53db3aeee5d4609be70ebf6a7e305ce30b13d34a09c7e7c1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "06fd68a3d25f7a54dc5272a70466f38bdd127a8ac4be2c6b0de30c43c14516d2", "generation_seconds_batch": 24.841172161977738, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17263329029083252, "target_z": -0.3007812543589173, "ce": 6.086154937744141, "genuineness": 4.413206577301025, "identity": 0.5891344547271729, "hypothesis": "Ik 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_Emotional_Numbness/2473427ee93e8f8a53db3aeee5d4609be70ebf6a7e305ce30b13d34a09c7e7c1.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "252fad64a2d4a322e91460da14a36d329c54bbaad74e3947860d75e8b341d8a9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1e91ac329ad04a184e92a4e0dc3f2bccad110f75cdfee2aaa266f0abdd2f4816", "generation_seconds_batch": 18.165423641097732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3576028645038605, "target_z": -0.1083984378632431, "ce": 6.109982967376709, "genuineness": 4.921566009521484, "identity": 0.7414867877960205, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/252fad64a2d4a322e91460da14a36d329c54bbaad74e3947860d75e8b341d8a9.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": "254b6f77044c8d0abb1501c6b4fcc0c0e8cebd3c53d3294f88cbe47813501261", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "62c0dc865cfcdc0d1bb41b89cfcf630a4371bb762df60070f86f725ad16f506b", "generation_seconds_batch": 18.19565807003528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26277077198028564, "target_z": -0.20703122723676542, "ce": 5.434855937957764, "genuineness": 4.720732688903809, "identity": 0.6917295455932617, "hypothesis": "Que quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/254b6f77044c8d0abb1501c6b4fcc0c0e8cebd3c53d3294f88cbe47813501261.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "2613c48aca8e9ee1e5790de6497d73384803f48dc0278520efb1f361872a035b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac40a2140e44d772ed5c6feb70aac20bfbbdc6acdf9c95674a06fca4755172b4", "generation_seconds_batch": 23.273611894925125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23648065328598022, "target_z": -0.2343750058118897, "ce": 5.9431867599487305, "genuineness": 4.231201171875, "identity": 0.6620051264762878, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2613c48aca8e9ee1e5790de6497d73384803f48dc0278520efb1f361872a035b.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "155d6c67b6dcc03e97deee41b85cc8efe16d682bcb207ff6fe1bda8961e2e239", "generation_seconds_batch": 17.94133065699134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1594882607460022, "target_z": -0.3144531126497344, "ce": 6.483288764953613, "genuineness": 4.406930446624756, "identity": 0.27301254868507385, "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_Emotional_Numbness/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "26e9f6a6cce9c65f2d7b4a8ffbc992bb14492c5ca12030ccc62697c603595d6f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6683846ffe5834e683b75815cfdc587d42d1dace73838ee74675de6cf82be960", "generation_seconds_batch": 18.133777698036283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23741959035396576, "target_z": -0.2333984378632431, "ce": 6.268836498260498, "genuineness": 4.532451152801514, "identity": 0.49427908658981323, "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_Emotional_Numbness/26e9f6a6cce9c65f2d7b4a8ffbc992bb14492c5ca12030ccc62697c603595d6f.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "2783508b3033540604ea0d36746dc76f935a5262188b31f0f57800193847cbe0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b3af18aaa29c53cbeae0001dba65f861e48c0462b3d18edd18e0d4d7e3afc31", "generation_seconds_batch": 26.050170053029433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3421104848384857, "target_z": -0.12451172377486296, "ce": 5.982900142669678, "genuineness": 4.306513786315918, "identity": 0.6011228561401367, "hypothesis": "Ik 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_Emotional_Numbness/2783508b3033540604ea0d36746dc76f935a5262188b31f0f57800193847cbe0.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "27c9530077d3d3f0d8974b0c9f157911b2d46d9045338d09999b5d53852d18bf", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "aed3c3c64c792295d8392f67d383fd8ca393b6158e0684e4247372804832cb16", "generation_seconds_batch": 23.284962383913808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16324397921562195, "target_z": -0.3105468718518931, "ce": 6.022613525390625, "genuineness": 4.595211505889893, "identity": 0.3960566520690918, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/27c9530077d3d3f0d8974b0c9f157911b2d46d9045338d09999b5d53852d18bf.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "27da2371dc628dd3e29ebebbd7f0bcc5e91cb26759c368c008df7c97df02262a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "27585ba0da933df47d2af2cb7b11d32a64ae60c9311e7ad7e43009297b2ade02", "generation_seconds_batch": 21.89081387303304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2768547236919403, "target_z": -0.19238281649567415, "ce": 6.046441555023193, "genuineness": 4.344170093536377, "identity": 0.7707946300506592, "hypothesis": "Ik 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_Emotional_Numbness/27da2371dc628dd3e29ebebbd7f0bcc5e91cb26759c368c008df7c97df02262a.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "2807653793595a88a56dfede325411d530ee5bd6430b424648f3acca5076a4dd", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3f321ddb8de6fb9f1f8e19f33465823da59a3c26579aae99121ceff7e902a23b", "generation_seconds_batch": 19.18657450005412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12005311250686646, "target_z": -0.35546874951567586, "ce": 6.284721851348877, "genuineness": 4.432034492492676, "identity": 0.5633851289749146, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2807653793595a88a56dfede325411d530ee5bd6430b424648f3acca5076a4dd.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "286c4b49d2e6a58aef6e1705923ed42ca3d72d2fdce7cfdc00d9762126ead189", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05de3ce77854cc8278b2c71c65db25890736309ca6049c991af780fc6ed94005", "generation_seconds_batch": 22.777322061010636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3219234347343445, "target_z": -0.1455078339313432, "ce": 5.903473377227783, "genuineness": 4.7834930419921875, "identity": 0.5802969336509705, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/286c4b49d2e6a58aef6e1705923ed42ca3d72d2fdce7cfdc00d9762126ead189.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "28c8e916981c2683fa7fa581a7c7b9d4b6ced7988e0887bd3ddbec4310031a84", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fae2ace1f42a07eff0429da0f77aacf95e2598499b09221c162e3a721d25e04c", "generation_seconds_batch": 18.624280560063198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2411753237247467, "target_z": -0.22949218156702927, "ce": 6.181467056274414, "genuineness": 4.494794845581055, "identity": 0.3200467824935913, "hypothesis": "The 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_Emotional_Numbness/28c8e916981c2683fa7fa581a7c7b9d4b6ced7988e0887bd3ddbec4310031a84.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "28dfef6f0c925571beeed2950042b88eb0d082ca5673211baaad1f81703edaf3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7186e44e28c56cf5f5a8fe942ac4ad4ce30de77ba2bbfc886b2a278a61d92ea7", "generation_seconds_batch": 18.827792212017812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43670788407325745, "target_z": -0.026123033767977956, "ce": 5.903473377227783, "genuineness": 4.821148872375488, "identity": 0.7302889823913574, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/28dfef6f0c925571beeed2950042b88eb0d082ca5673211baaad1f81703edaf3.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "298634c3b4c30cc51bb72e08bab2e5c1b9cc9b62546a0ade5b23bbb7459b25df", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7d2ccfcf4002809dc6ec8cc02216e358d877ece394651060217cb3c9ba858184", "generation_seconds_batch": 24.876118966960348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07686224579811096, "target_z": -0.4003906271794586, "ce": 6.324435234069824, "genuineness": 4.3881025314331055, "identity": 0.4632890820503235, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/298634c3b4c30cc51bb72e08bab2e5c1b9cc9b62546a0ade5b23bbb7459b25df.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "2a128ac0ad996b1b7263ba31ba9750ac87121675d6015a9f60788042d19c83e2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29bbcc24bced359cb57a4fc2d6852ea2716a5721e69b31bdb9dba710e5f9845a", "generation_seconds_batch": 23.203048930037767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5047804117202759, "target_z": 0.044677716303655524, "ce": 6.086154937744141, "genuineness": 3.9927117824554443, "identity": 0.6259574890136719, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2a128ac0ad996b1b7263ba31ba9750ac87121675d6015a9f60788042d19c83e2.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "2a8542deda27403cc3fc4a6e453c98e4ec57718c592a4601ec0849f27ba81c34", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4b154c17ce056af8d20ada4a471af127218f6f8dfe2f764a46e610bbe158f947", "generation_seconds_batch": 24.448036584071815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7566488981246948, "target_z": 0.30664063105405176, "ce": 5.22636079788208, "genuineness": 4.821148872375488, "identity": 0.6604785323143005, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/2a8542deda27403cc3fc4a6e453c98e4ec57718c592a4601ec0849f27ba81c34.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "2b09628d5b862dda6a5369c415eb554bed1537679d72e4ed001a6dc68b5c4196", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9a03fa2abb2738296dd076453799aa2731dd283110b67c8f972424ee0097a7e", "generation_seconds_batch": 24.969033970031887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34164100885391235, "target_z": -0.12500001549837247, "ce": 6.054384231567383, "genuineness": 4.394378662109375, "identity": 0.7042095065116882, "hypothesis": "Ik 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_Emotional_Numbness/2b09628d5b862dda6a5369c415eb554bed1537679d72e4ed001a6dc68b5c4196.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "2b888c0c85077954524ce3fe8079b04ab7023963d5db6f7c6c835ddeb1b5ab41", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cbc69f149ef458b8b29294c3f527f584d7acbfc7fbffd6af20c2ebcf28cfd8ef", "generation_seconds_batch": 27.119999110000208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24211424589157104, "target_z": -0.2285156291167552, "ce": 5.982900142669678, "genuineness": 4.770940780639648, "identity": 0.8274149894714355, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2b888c0c85077954524ce3fe8079b04ab7023963d5db6f7c6c835ddeb1b5ab41.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "2bd398eea83974075f1a7dc94ac04fd0f6ca07fe4ad6c38c7cf8ac608dd73e14", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "515078808391de786240487c7a129aa52bd36cb8421da5cccbb84b889ff023c7", "generation_seconds_batch": 23.77990686800331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09751874208450317, "target_z": -0.37890625629621383, "ce": 6.443574905395508, "genuineness": 4.432034492492676, "identity": 0.39670056104660034, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2bd398eea83974075f1a7dc94ac04fd0f6ca07fe4ad6c38c7cf8ac608dd73e14.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": "2bdba2a95bb1a35c32e3e8979991867ad6c2b251c6798025b2fec43204eb6b39", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "955701b5b00a86a2a9dc454af29743df6b55658f4ceefcf4997628a527fafb62", "generation_seconds_batch": 18.19565807003528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30126696825027466, "target_z": -0.16699217381784304, "ce": 5.649308204650879, "genuineness": 4.883909225463867, "identity": 0.838833212852478, "hypothesis": "Quelqu'un déplaçait, la petite chaise bleue. Elle était ici près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2bdba2a95bb1a35c32e3e8979991867ad6c2b251c6798025b2fec43204eb6b39.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "2c1ceb9412cb6a8d66f08e2112ba44ff89f6e8407530064d8dbbb576506eb338", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2c0405900a1713512feae52a874734218ea9999ba8c2cdf9dfe01546a886a385", "generation_seconds_batch": 23.149232438066974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052450031042099, "target_z": -0.42578123886054475, "ce": 6.41180419921875, "genuineness": 4.400654315948486, "identity": 0.3419749140739441, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2c1ceb9412cb6a8d66f08e2112ba44ff89f6e8407530064d8dbbb576506eb338.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "2cc8dd58ac60e036621588a1d99f75391e133ef4ba96101617d8b6cd95e9d836", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8976d44feedbffced2fbf494f155de6a99b6361dfc51dfe9fc4eba7d1319ef21", "generation_seconds_batch": 24.66542209708132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2233356088399887, "target_z": -0.24804687960107932, "ce": 5.959072113037109, "genuineness": 4.469690799713135, "identity": 0.6734192967414856, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude Dente Raam. We kunnen daar 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_Emotional_Numbness/2cc8dd58ac60e036621588a1d99f75391e133ef4ba96101617d8b6cd95e9d836.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "2d0e735780e65a0f04db218b35c25271c2befc35ebbb88a30433d20c68c0158c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "685b30bd735f12a2a843f4f6c82cbdce43d7906291d1bc955a7964c4464b70bf", "generation_seconds_batch": 26.325569272972643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23929744958877563, "target_z": -0.23144531746432243, "ce": 6.419747352600098, "genuineness": 4.557555198669434, "identity": 0.6529361009597778, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2d0e735780e65a0f04db218b35c25271c2befc35ebbb88a30433d20c68c0158c.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "2d9e1472b09a6744cd8eb55115700cc1dd17199ba2a9d20fc488480f0d06c779", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d8a68d3cf813913fab0879d021169e684d2215a58042c504288552940b0c9442", "generation_seconds_batch": 25.178610904025845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19892337918281555, "target_z": -0.27343750678053796, "ce": 6.046441555023193, "genuineness": 4.582659721374512, "identity": 0.4647362232208252, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2d9e1472b09a6744cd8eb55115700cc1dd17199ba2a9d20fc488480f0d06c779.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "2ecd6dac8cf13982bd7e033df0a0d8f7e38fbb99edc8996dd260b99687bb2981", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "04247d1a12c9f13406f5e1a83597e19e52103c1d42778e3e44d1d08cde7a4703", "generation_seconds_batch": 25.546151370042935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12756457924842834, "target_z": -0.3476562369232482, "ce": 6.260893821716309, "genuineness": 4.3504462242126465, "identity": 0.18195737898349762, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2ecd6dac8cf13982bd7e033df0a0d8f7e38fbb99edc8996dd260b99687bb2981.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": "2ee404819a06cbb431170a5dae620847ef231b659eabce40f6b79db5a85652f8", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "2dfb2d0be3df7629f1d03e767be2ada39d1789b19b47ae58ff433a47ba603645", "generation_seconds_batch": 19.75923647894524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6082976460456848, "target_z": 0.15234373208000682, "ce": 5.657250881195068, "genuineness": 4.68307638168335, "identity": 0.760381817817688, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal. Dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2ee404819a06cbb431170a5dae620847ef231b659eabce40f6b79db5a85652f8.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "2ee4479097bd8747e880e673e63c212b2217134086fe9284f170dce3f2107df0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1c698f109962dbea063dccb6472b003100b4c7c65bf89e5f01177f14e98f9673", "generation_seconds_batch": 19.470005646930076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12193098664283752, "target_z": -0.3535156136183827, "ce": 6.221180438995361, "genuineness": 4.519899368286133, "identity": 0.1621805727481842, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2ee4479097bd8747e880e673e63c212b2217134086fe9284f170dce3f2107df0.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "2f0880e3efd4be77665493009665e0536b2d9b0905e61c17c464d722b5d3b5e1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "983d77c6231482b255ce33c1c1ef98595ef887d93656f7b9bbaa31c6b5cd72b4", "generation_seconds_batch": 25.44388528598938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4466840326786041, "target_z": -0.015747059369801458, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.7857418060302734, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/2f0880e3efd4be77665493009665e0536b2d9b0905e61c17c464d722b5d3b5e1.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": "2f18bb1bc745e42b0263edaa7c307bc6c2c8e0e4b37dafb4bd1b702d5f2e8d92", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "986c6a425ece02127509a4596db41665fdbd9a06826b1f3434eb1df678e7453f", "generation_seconds_batch": 18.629826614051126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6064198017120361, "target_z": 0.15039062717945864, "ce": 5.919358730316162, "genuineness": 4.557555198669434, "identity": 0.4530891478061676, "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_Emotional_Numbness/2f18bb1bc745e42b0263edaa7c307bc6c2c8e0e4b37dafb4bd1b702d5f2e8d92.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "2fb60b1f3b3c53280cd3ed6f12f168c19a9a7e2c7a3abd3c330fffd4c840a1bf", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "34ad77839a136ab57eb4411aaf66687d78b1ad9ff678fe4dc251a5c15981277b", "generation_seconds_batch": 20.450155840953812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19892337918281555, "target_z": -0.27343750678053796, "ce": 6.054384231567383, "genuineness": 4.425758361816406, "identity": 0.7333319187164307, "hypothesis": "La porte 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_Emotional_Numbness/2fb60b1f3b3c53280cd3ed6f12f168c19a9a7e2c7a3abd3c330fffd4c840a1bf.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "30248d25b6531040f6a35d39a34c76b32d6d7d141a1af7cb283babc645a7a3f6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "93fd1e430f01069a7056cd57477cb6f923a84d404f6190c49d26a8fc6a2ca669", "generation_seconds_batch": 26.351399013074115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23741959035396576, "target_z": -0.2333984378632431, "ce": 5.990842819213867, "genuineness": 4.871357440948486, "identity": 0.6532855033874512, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/30248d25b6531040f6a35d39a34c76b32d6d7d141a1af7cb283babc645a7a3f6.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "305188cea1dcfe6ea74214d9db82c7b3d00e8f1b38f0f4085f852eab9647c8a4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "95fdf04ce546d7ef841a1ef143c20e86107d69f2bf9246f01bd4d85daef90d3b", "generation_seconds_batch": 24.091997882002033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6233205795288086, "target_z": 0.1679687572648621, "ce": 6.006728172302246, "genuineness": 4.7458367347717285, "identity": 0.7889357805252075, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/305188cea1dcfe6ea74214d9db82c7b3d00e8f1b38f0f4085f852eab9647c8a4.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "30bafdf0f77c08bc8c42ff14884d347270a2f4f9e58a89e1bbc9a10b08db6825", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9e89a3de985ce662c3bbff882b5b0bb9474c5a4347f896fec0415b3d2faa7633", "generation_seconds_batch": 21.763379907002673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4435151219367981, "target_z": -0.019042974259187093, "ce": 6.046441555023193, "genuineness": 4.645420074462891, "identity": 0.6743777394294739, "hypothesis": "La porte 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_Emotional_Numbness/30bafdf0f77c08bc8c42ff14884d347270a2f4f9e58a89e1bbc9a10b08db6825.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "30dff57d427f9076008fc33c34ac490ee2653853d90272e009380323988d1054", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "51ef5cfc8ac6779bd77a5b5c1f17eb38be97474ca11ffc165b65550cb92a5b02", "generation_seconds_batch": 24.86101613100618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6242594718933105, "target_z": 0.1689452787183912, "ce": 6.078212261199951, "genuineness": 4.7458367347717285, "identity": 0.8231180906295776, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/30dff57d427f9076008fc33c34ac490ee2653853d90272e009380323988d1054.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "30e3d3dcad5bbd92bbf1873ed366ab147e1f39f204a26537d981a856bf69f0f1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "191b40184fa9590ff98bab7a6ac8a8ca3567956d5dfafdae040fc00716e7e43a", "generation_seconds_batch": 25.95370765600819, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2383585274219513, "target_z": -0.23242186991459654, "ce": 6.070269584655762, "genuineness": 4.65797233581543, "identity": 0.6079341173171997, "hypothesis": "La porte 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_Emotional_Numbness/30e3d3dcad5bbd92bbf1873ed366ab147e1f39f204a26537d981a856bf69f0f1.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "30ec8022e40ca864de3974cb13b4f55656f3534da0d84822febded177f4f55fc", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "55498c1be2de45bc56ca3b23d63276522256ab734b2193c27ebdcc8dd7f7faa8", "generation_seconds_batch": 25.224670091993175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6965572834014893, "target_z": 0.24414065430161047, "ce": 5.903473377227783, "genuineness": 4.7834930419921875, "identity": 0.7321913838386536, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/30ec8022e40ca864de3974cb13b4f55656f3534da0d84822febded177f4f55fc.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "31420ae7db855babb7d07aa8b0d50f61dd8d6a0e1b584b60eb3fa65d19308bc5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "deb443aa5a6982c92e202273f1f6524c5c4aa48ab1b98da40eab45f016a5279c", "generation_seconds_batch": 22.93450038204901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.976358950138092, "target_z": 0.535156260170807, "ce": 5.4666266441345215, "genuineness": 4.7834930419921875, "identity": 0.7966331243515015, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/31420ae7db855babb7d07aa8b0d50f61dd8d6a0e1b584b60eb3fa65d19308bc5.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "31b8076da2bf67920acfd9565cf86fed6a3410a66f9f883e0ac4c720d98c290c", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6100ccced6b63989d91a20b0187796a2a67cfd57463b2804dafbc179300f18c7", "generation_seconds_batch": 18.069172856980003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5848243832588196, "target_z": 0.12792970384593974, "ce": 5.855817794799805, "genuineness": 4.293961524963379, "identity": 0.5354633331298828, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/31b8076da2bf67920acfd9565cf86fed6a3410a66f9f883e0ac4c720d98c290c.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "31da874fbb18141004e67f789a534178eaf048bb9edbf044ff03eb6de6dcdb98", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "633c04f3ee4f6ba38ab3d4fceda029355b009de108e3aba2a27f9c2dfbcf3198", "generation_seconds_batch": 23.07705054699909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13695389032363892, "target_z": -0.3378906194302724, "ce": 5.903473377227783, "genuineness": 4.469690799713135, "identity": 0.5032790899276733, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/31da874fbb18141004e67f789a534178eaf048bb9edbf044ff03eb6de6dcdb98.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "31fa92eabcf918dbad087c10f728b549cfa54bc536f58118d751b0312fd482be", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "08e3bf166713f7bf495c4856bd0d3729568374a8a87ab09b492090d432885e3c", "generation_seconds_batch": 23.07705054699909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24211424589157104, "target_z": -0.2285156291167552, "ce": 6.284721851348877, "genuineness": 4.7332844734191895, "identity": 0.24890585243701935, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/31fa92eabcf918dbad087c10f728b549cfa54bc536f58118d751b0312fd482be.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "325f4cbda4edc2e1e7ae663c179b332a64619b4745cb4d295897c925b8b5e6ef", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "01d893108d0c89b2a1e708ac8a7d920ffd7bce54681c43398ed3085e3c86a503", "generation_seconds_batch": 25.492491937009618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08249583840370178, "target_z": -0.39453125048432414, "ce": 6.38003396987915, "genuineness": 4.595211505889893, "identity": 0.24195468425750732, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/325f4cbda4edc2e1e7ae663c179b332a64619b4745cb4d295897c925b8b5e6ef.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "32718f1053f4f6cf27700ff22311724fcfc2a9ddcb572e4e7499696506c6ff4f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "621dbf0cccd9f493d612709213936fafcf0144acd773bb8859703299212c331e", "generation_seconds_batch": 24.377507732016966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26277077198028564, "target_z": -0.20703122723676542, "ce": 5.760505676269531, "genuineness": 4.770940780639648, "identity": 0.7538491487503052, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/32718f1053f4f6cf27700ff22311724fcfc2a9ddcb572e4e7499696506c6ff4f.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "328fdf4ceca7e39f8bf006eef217d7d30d5d55eac9de8f5b127e8672eafbebf5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "99cc88b16e1f972d3d700a8d13484a20dbfbf6567acb0269a1ecdd2a266ee8f1", "generation_seconds_batch": 22.394712947076187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1078094244003296, "target_z": 0.6718750290594484, "ce": 5.903473377227783, "genuineness": 4.381826400756836, "identity": 0.253201425075531, "hypothesis": "Ik 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_Emotional_Numbness/328fdf4ceca7e39f8bf006eef217d7d30d5d55eac9de8f5b127e8672eafbebf5.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "32ab7ec1acd42c6960e2d6c756d04d575659ea1ef18a4c3d72c9f8aa9f027b11", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4a2270de3c68e0fee55d8b030dedcbbd3d93bf0b64c2d65c9f7809fe904ddeb6", "generation_seconds_batch": 22.924465373973362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35478606820106506, "target_z": -0.11132812621081035, "ce": 5.752562999725342, "genuineness": 4.808597087860107, "identity": 0.652768611907959, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/32ab7ec1acd42c6960e2d6c756d04d575659ea1ef18a4c3d72c9f8aa9f027b11.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": "32bb46380ca3efe40d5848d3c69a79fbc3128b3b74ec51f7a065af798a2545fc", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The keys are on the kitchen table.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c0a147aa2ef21810b982aaa53d899c6319f6459a192d50bbdad316c086b46797", "generation_seconds_batch": 19.019334623008035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28342723846435547, "target_z": -0.18554688735026556, "ce": 6.125868320465088, "genuineness": 4.545003414154053, "identity": 0.3918483853340149, "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_Emotional_Numbness/32bb46380ca3efe40d5848d3c69a79fbc3128b3b74ec51f7a065af798a2545fc.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "32c07d1f5c869f2f76ad4964e08c3d2e7e5e652f3a2f6bb7e5835eb05f8faa59", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "899e50ed1177543503c27bd63539ef6d20e6ee9edab3eb245d416be67bc19268", "generation_seconds_batch": 23.004492571926676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0599614679813385, "target_z": -0.4179687572648621, "ce": 6.4515180587768555, "genuineness": 4.557555198669434, "identity": 0.32101017236709595, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/32c07d1f5c869f2f76ad4964e08c3d2e7e5e652f3a2f6bb7e5835eb05f8faa59.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "32e7755dabb116c769474f237893214433f0e1b3b5c305ce4b7c0e8ea0b353c7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6f48e1211022e86fb8a660cc52b0549f5acda81e5032d41522448c02a9ccf760", "generation_seconds_batch": 27.119999110000208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22427454590797424, "target_z": -0.24707031165243276, "ce": 5.788304805755615, "genuineness": 4.7332844734191895, "identity": 0.7168769836425781, "hypothesis": "He encontrado la cajita. Estaba junto a la vana 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_Emotional_Numbness/32e7755dabb116c769474f237893214433f0e1b3b5c305ce4b7c0e8ea0b353c7.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "338d3b07405d4369e2162cef3e896c5835920ce5206b8596add636907f911e33", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d99809f03b404f63db3fa79972d1d4bed149dbe50f53bc11a113fb0a50b6d05e", "generation_seconds_batch": 25.851937155006453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21957989037036896, "target_z": -0.25195312039892065, "ce": 5.982900142669678, "genuineness": 4.582659721374512, "identity": 0.7003644704818726, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/338d3b07405d4369e2162cef3e896c5835920ce5206b8596add636907f911e33.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "33945e5b78d546dfd17eb63f41a2eb3bcb73e621b6927229c1a9d8e9e176c266", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "df629e29e2a9ec367b29e27ef71ef4af08b153fabb00f5055dda272c88d164f5", "generation_seconds_batch": 23.8420006360393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15385466814041138, "target_z": -0.3203124893448689, "ce": 6.1894097328186035, "genuineness": 4.7834930419921875, "identity": 0.597592830657959, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/33945e5b78d546dfd17eb63f41a2eb3bcb73e621b6927229c1a9d8e9e176c266.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "33ddb296dc389137505cd30a2785a145e3b653893d36203be7fef8762ea7536a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "651ba7a2e5c040875c46a83becf91a4bbd468508c88559b6c48a7599bc566ec5", "generation_seconds_batch": 24.567669773008674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45759910345077515, "target_z": -0.004394532521350868, "ce": 5.784333229064941, "genuineness": 4.68307638168335, "identity": 0.7457541227340698, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/33ddb296dc389137505cd30a2785a145e3b653893d36203be7fef8762ea7536a.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "8b4665ad6e876eafd8349b8890d92739d406e581ccdbdebd97a35dabf16d71b4", "generation_seconds_batch": 16.465619422961026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17826688289642334, "target_z": -0.29492187766378275, "ce": 6.173524379730225, "genuineness": 4.432034492492676, "identity": 0.6202532052993774, "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_Emotional_Numbness/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "3461751aec031c3bbb6fe03aaa80300c0838612c0dcd247c0607c9a448e54703", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "32808e3c46d5999682028d5d4a14838e6e0bd5b0b08f81e7dff67ac85e1d23ee", "generation_seconds_batch": 23.128716851002537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1313202977180481, "target_z": -0.34374999612540685, "ce": 6.284721851348877, "genuineness": 4.595211505889893, "identity": 0.32440119981765747, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3461751aec031c3bbb6fe03aaa80300c0838612c0dcd247c0607c9a448e54703.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "3468089a0279267c80c6167422a92d12e70e7bcae304399a16c4e5e9decfdec0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "95db9256050799fde6a09b9651ef849b94f5da679ba849d56849405d4647f73a", "generation_seconds_batch": 22.707526679965667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12193098664283752, "target_z": -0.3535156136183827, "ce": 6.197352409362793, "genuineness": 4.457139015197754, "identity": 0.6869367361068726, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/3468089a0279267c80c6167422a92d12e70e7bcae304399a16c4e5e9decfdec0.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "347349da2d1c438fbc210914bda57f3d34f28859feb6be784bf00deeede1f6fd", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "044fbe3c103deb92784648fb15fe06699611738f99544b23ae603f3f36ddd6f8", "generation_seconds_batch": 24.874736479949206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44562771916389465, "target_z": -0.01684570799851166, "ce": 5.752562999725342, "genuineness": 4.632867813110352, "identity": 0.6171411275863647, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/347349da2d1c438fbc210914bda57f3d34f28859feb6be784bf00deeede1f6fd.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "afca2c611074e5eed167df6b8eeb32d5fd4b389faa4e95b3f86be6ba950678c6", "generation_seconds_batch": 17.70674896100536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20080125331878662, "target_z": -0.2714843708832448, "ce": 6.427689552307129, "genuineness": 4.105680465698242, "identity": 0.2631518840789795, "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_Emotional_Numbness/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "34baa3680af9c3fa0fd219b481176c54964e85b25c1d00f33683d5ba0e4308d9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "147d5b2358f8c8ef2b8a9fcb2ef2f6f0b6262e9544e30427ac5bcee3285522da", "generation_seconds_batch": 25.057062993058935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5061888098716736, "target_z": 0.04614256047743914, "ce": 5.839932441711426, "genuineness": 4.494794845581055, "identity": 0.6648752689361572, "hypothesis": "De deur 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_Emotional_Numbness/34baa3680af9c3fa0fd219b481176c54964e85b25c1d00f33683d5ba0e4308d9.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "3500f15457fbd822b0ae36b559b7c3757b012163a1176ddcee836c7daf7cba9a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c7ecee09eb6601fa1b9bc457653a7d77c0dc251ae35b121848a4baffcada33c5", "generation_seconds_batch": 15.27863165398594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2411753237247467, "target_z": -0.22949218156702927, "ce": 6.133810997009277, "genuineness": 4.494794845581055, "identity": 0.4292750060558319, "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_Emotional_Numbness/3500f15457fbd822b0ae36b559b7c3757b012163a1176ddcee836c7daf7cba9a.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "3511cbb43d9f022372b8e7874e4c6b438a92a9fbfc6c5ec4eacee7b05dfac5e7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2ff774becee65bac227f39a3cac9b5f519fa937dd960bb513a31589954e72a27", "generation_seconds_batch": 25.34271958505269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6580610275268555, "target_z": 0.20410153888919816, "ce": 5.7684478759765625, "genuineness": 4.419482707977295, "identity": 0.7015373706817627, "hypothesis": "De deur 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_Emotional_Numbness/3511cbb43d9f022372b8e7874e4c6b438a92a9fbfc6c5ec4eacee7b05dfac5e7.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "351d4d4f04301cb040537e1df46e9acf7b130aac58031eeb4a554c5ac7efb21b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f724627c385904ba1c6dcca882a63a28c1c06cae1ce955aafb421eeade25375b", "generation_seconds_batch": 26.276892377994955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4840065538883209, "target_z": 0.02307128023871957, "ce": 5.919358730316162, "genuineness": 4.632867813110352, "identity": 0.6171637773513794, "hypothesis": "Ik 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_Emotional_Numbness/351d4d4f04301cb040537e1df46e9acf7b130aac58031eeb4a554c5ac7efb21b.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": "35799fcab0e8c578e4aa5b3a14ae928e30a172480d6d608eeac1d9cfd518a0cf", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "170b4feb9589f5c2f5eeb9344add8e92e2c2ca3b2d1879222dedff24602593b2", "generation_seconds_batch": 26.98023581900634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3824845552444458, "target_z": -0.08251953445864743, "ce": 5.692992687225342, "genuineness": 4.68307638168335, "identity": 0.7662683725357056, "hypothesis": "Quelqu'un est déplacé, la petite chaise bleue, elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/35799fcab0e8c578e4aa5b3a14ae928e30a172480d6d608eeac1d9cfd518a0cf.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "3586f80f30c17c06c68f75ed985fcc1f7acc5bcae8f4a9f15d2bf927b9ced3ab", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "553a11e04009a139af209e810d7897f92a88ed84e0b5cce4d03ff4802d558b34", "generation_seconds_batch": 23.690810365020297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23366385698318481, "target_z": -0.23730469415945693, "ce": 6.141753673553467, "genuineness": 4.6203155517578125, "identity": 0.6083551049232483, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3586f80f30c17c06c68f75ed985fcc1f7acc5bcae8f4a9f15d2bf927b9ced3ab.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "3646483073671125b08c4e7420df59f6ae908f9b1e02823ba835f76b31fd424a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cc417e5cf237b0e7cdc3a7b3b4dbe901d4aa9b28007b0feef63e82400f0c39ce", "generation_seconds_batch": 25.65041534404736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18390047550201416, "target_z": -0.2890625009686483, "ce": 5.967014789581299, "genuineness": 4.808597087860107, "identity": 0.8464288115501404, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/3646483073671125b08c4e7420df59f6ae908f9b1e02823ba835f76b31fd424a.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "36729cdff6e66f3d0bc632ec53f79c58687b64f83fa3b9c18f35df31bde08eee", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c7f7217eff8a18e62f68343264f8857856ecf28839814591ea4737b3fcaa070a", "generation_seconds_batch": 25.10575114598032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4212155044078827, "target_z": -0.0422363196795978, "ce": 5.998785495758057, "genuineness": 4.494794845581055, "identity": 0.3242257237434387, "hypothesis": "De deur 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_Emotional_Numbness/36729cdff6e66f3d0bc632ec53f79c58687b64f83fa3b9c18f35df31bde08eee.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "36d8076156867e822744d84f19e2a4f0e1ddf644cff03c5b5412c0f3e8716dde", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d13634a7c93d1513037acf77f74b042b1a63740a4c3a647705662676977c3153", "generation_seconds_batch": 25.352198349079117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1669996976852417, "target_z": -0.30664063105405176, "ce": 6.046441555023193, "genuineness": 4.356721878051758, "identity": 0.3304610848426819, "hypothesis": "The 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_Emotional_Numbness/36d8076156867e822744d84f19e2a4f0e1ddf644cff03c5b5412c0f3e8716dde.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "372ec456873183bdbe1ac5404680c44df6445041a1884417588eb1b184884e00", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "876d2daf0a05c6e6351e09637279bc2ffe5ed83145997713056ade14994ca9c5", "generation_seconds_batch": 17.947392225032672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2383585274219513, "target_z": -0.23242186991459654, "ce": 5.677107334136963, "genuineness": 4.137060642242432, "identity": 0.37343278527259827, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/372ec456873183bdbe1ac5404680c44df6445041a1884417588eb1b184884e00.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "3796ff5516ca9cf3597a346a60c92f2d80b95c885d9953be8c48a5b597b71178", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8bc323917634f92a810469224623465e8fa2a1d33a80f26bcb0b1b3079b43f34", "generation_seconds_batch": 24.347672760952264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15573251247406006, "target_z": -0.3183593844443207, "ce": 6.117925643920898, "genuineness": 4.632867813110352, "identity": 0.6151671409606934, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3796ff5516ca9cf3597a346a60c92f2d80b95c885d9953be8c48a5b597b71178.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "3865121f8c7f40cf039882c6dda9e468e8b5862dcc4b1c3f98e53c5f6044a32a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "29fb242d0bbae6f90735e23e240cb0e5c896893757a3f9c79a0473833e467fbf", "generation_seconds_batch": 25.68143981695175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15009891986846924, "target_z": -0.32421876113945525, "ce": 6.046441555023193, "genuineness": 4.7834930419921875, "identity": 0.8309730291366577, "hypothesis": "La porte 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_Emotional_Numbness/3865121f8c7f40cf039882c6dda9e468e8b5862dcc4b1c3f98e53c5f6044a32a.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "387a79b7b72552922daf29ff425681cb35b214e0deb4b78c27aae4b2bbc609af", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "45a08a8a2090c8b2f559cea3d1b38e3b9e5298f36ab922e2f7f18b33ca306fb3", "generation_seconds_batch": 23.799785634037107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10878592729568481, "target_z": -0.3671875029059448, "ce": 6.308549880981445, "genuineness": 4.118232727050781, "identity": 0.09285113215446472, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/387a79b7b72552922daf29ff425681cb35b214e0deb4b78c27aae4b2bbc609af.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "391d2c88bf66c8a20d84ca77785f444afac763b374c20165bc3f44a992e62617", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e3c30323d72713eb7f0124bb6d33324db5109209edd0b58a84b5d8aa3908c01", "generation_seconds_batch": 25.419141323072836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3097173571586609, "target_z": -0.1582031087751413, "ce": 5.927301406860352, "genuineness": 4.7081804275512695, "identity": 0.5900508165359497, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/391d2c88bf66c8a20d84ca77785f444afac763b374c20165bc3f44a992e62617.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "39f017373aa20c7d9ec1068119a526c7255e7970e42729baf527426aad1a7acb", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "baf554b5d9f4815be570e526fe485a8243a126326de99726dd659cb74d41b72e", "generation_seconds_batch": 25.48772083001677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19892337918281555, "target_z": -0.27343750678053796, "ce": 6.1894097328186035, "genuineness": 4.7458367347717285, "identity": 0.8283170461654663, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/39f017373aa20c7d9ec1068119a526c7255e7970e42729baf527426aad1a7acb.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "3a632606d241b2c157ef5176627b168bec1ca5f9482314bcf2ebc049406deade", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "dba629cfaf0e33ad0a68c42ed82c23f8771e93c758a70048e50181958d567c58", "generation_seconds_batch": 22.777322061010636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21206843852996826, "target_z": -0.25976561749297583, "ce": 6.149696350097656, "genuineness": 4.833701133728027, "identity": 0.7140836119651794, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3a632606d241b2c157ef5176627b168bec1ca5f9482314bcf2ebc049406deade.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "3a7f71f6f564952cbf881b282f4ba852d1a9a078dd85bcaa273ef94291d0f8e9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "742dfcaf9ccb5e07dcefdf692d32c88d51da2f0eb36587553e6a1e211f782608", "generation_seconds_batch": 20.30322896700818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15573251247406006, "target_z": -0.3183593844443207, "ce": 6.157639026641846, "genuineness": 4.582659721374512, "identity": 0.5457324981689453, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3a7f71f6f564952cbf881b282f4ba852d1a9a078dd85bcaa273ef94291d0f8e9.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "3aa3fee668b697c7ee8b56a7394e9bb0da609b95f004f09251146ea307098c1f", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ca11dbbd242099e13261b70dcd71e387776ee1416ca952d4ede413261bfb7a58", "generation_seconds_batch": 16.860299329971895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11254164576530457, "target_z": -0.3632812621081035, "ce": 6.23706579208374, "genuineness": 4.645420074462891, "identity": 0.5128111839294434, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3aa3fee668b697c7ee8b56a7394e9bb0da609b95f004f09251146ea307098c1f.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": "3aad91f06f9e3678ca54825f8b2a5f092dc8f5d4f0fe1add01390aec1d63a53e", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "77db95d17c6a9754b0e296909b88b9e61689e6f2258521a695c37514b2ec3b28", "generation_seconds_batch": 25.137927028001286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.013916254043579, "target_z": 0.5742187921362002, "ce": 5.982900142669678, "genuineness": 4.532451152801514, "identity": 0.6314115524291992, "hypothesis": "Niemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3aad91f06f9e3678ca54825f8b2a5f092dc8f5d4f0fe1add01390aec1d63a53e.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "3abbb129354f04d14246abea76d1240c1466abb18a7de20cbd7188eab5962d36", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0713f61e5da07b1e3510e6d36d0137bae098356d8b5f8546483176cbec1cb2a0", "generation_seconds_batch": 25.617627715109847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13507601618766785, "target_z": -0.33984375532756556, "ce": 6.149696350097656, "genuineness": 4.532451152801514, "identity": 0.74445641040802, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/3abbb129354f04d14246abea76d1240c1466abb18a7de20cbd7188eab5962d36.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "3b1cb58fba31f1bad52ceee18472c25cbb23c777036f57d75cd92487678bf08f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7facb223d3bc613206a19d6d5654ebdbeef71f34356cffec4919d0be1dfeeaa6", "generation_seconds_batch": 25.552486127940938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4679860472679138, "target_z": 0.0064087010094895916, "ce": 6.213237762451172, "genuineness": 4.6203155517578125, "identity": 0.7754533290863037, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3b1cb58fba31f1bad52ceee18472c25cbb23c777036f57d75cd92487678bf08f.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "3b674de091faab15126aa101bf88fb26c4bf4277b2ef3d2503580663a1d49e89", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5301b03a94d36d76ba7b6f34440157594e674acc9cf269d081da79ba4b1f6b70", "generation_seconds_batch": 25.352198349079117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20080125331878662, "target_z": -0.2714843708832448, "ce": 6.165581703186035, "genuineness": 4.369274139404297, "identity": 0.15098538994789124, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3b674de091faab15126aa101bf88fb26c4bf4277b2ef3d2503580663a1d49e89.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "3b9713fc8cf372acf5060f7257132aeaa553cd207ea05e194a9e0187be7c27cd", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "366587b869bf503ecd8ee391376d4a073f9ff2483ef046c8b4b53f8170b13a7e", "generation_seconds_batch": 18.2757614570437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7716717720031738, "target_z": 0.3222655942454171, "ce": 5.744620323181152, "genuineness": 4.482243061065674, "identity": 0.5141581296920776, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3b9713fc8cf372acf5060f7257132aeaa553cd207ea05e194a9e0187be7c27cd.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "3c4ce7b150ddf2c118ff9fd672323d1451ae47fa226953045cbab2979621cb0f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "eb939b7e0c849daf47b0a0443c81cde627a06361add97a9a6671dee506a60f5c", "generation_seconds_batch": 19.470005646930076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12756457924842834, "target_z": -0.3476562369232482, "ce": 6.332377910614014, "genuineness": 4.394378662109375, "identity": 0.12801986932754517, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3c4ce7b150ddf2c118ff9fd672323d1451ae47fa226953045cbab2979621cb0f.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "98e9e9db868cc2f68e407e60dcdcab1e8ef3b99f2a919d7a071c7a89e862089c", "generation_seconds_batch": 17.59475459193345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25244247913360596, "target_z": -0.21777345917350527, "ce": 6.260893821716309, "genuineness": 4.369274139404297, "identity": 0.6875565052032471, "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_Emotional_Numbness/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "3c967facf27685d92c638235f8d59209cd8c1d02fca4ca077ea6efd4c0715056", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2d41b6d693cb60d57631665f0e1b74e8c8977bb93e8150c9e6daef6c74e74886", "generation_seconds_batch": 19.473334238980897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21394629776477814, "target_z": -0.2578124970940552, "ce": 5.824047088623047, "genuineness": 4.808597087860107, "identity": 0.7062389850616455, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/3c967facf27685d92c638235f8d59209cd8c1d02fca4ca077ea6efd4c0715056.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "3caf56b62f97d11826f0dcfd6d30712e06c06b5eb9c93aba33f3b5a9b296cc78", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ba81beef0241d55d7aad3991b6d6907d7b7d2d56d8eeff512c63a5ff9049b538", "generation_seconds_batch": 22.53731990302913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1951676607131958, "target_z": -0.2773437475783793, "ce": 6.221180438995361, "genuineness": 4.494794845581055, "identity": 0.2313322126865387, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3caf56b62f97d11826f0dcfd6d30712e06c06b5eb9c93aba33f3b5a9b296cc78.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "3d637389e72eb153500544844d9d81ea41770cf006aba54f54025b4d3138016a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "13ac1f5df606831818ee9ce8d6f55133a3b14d738a95094af99f86be8ecb5316", "generation_seconds_batch": 18.687050367007032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5036067366600037, "target_z": 0.043457002493254175, "ce": 5.5539960861206055, "genuineness": 4.846253395080566, "identity": 0.8539818525314331, "hypothesis": "La porte 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_Emotional_Numbness/3d637389e72eb153500544844d9d81ea41770cf006aba54f54025b4d3138016a.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "3dad6aa00674a885af49ba8dcb555e12287245f0357c1cb18bb2c088252dcfc4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3f5efe8e512534f48d26aac905552ed1196120613f423f62ba1d74109d7a6c79", "generation_seconds_batch": 25.178610904025845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.525202214717865, "target_z": 0.06591798782026302, "ce": 6.125868320465088, "genuineness": 4.632867813110352, "identity": 0.3375049829483032, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3dad6aa00674a885af49ba8dcb555e12287245f0357c1cb18bb2c088252dcfc4.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "3e05877501abc0dc58e7a7111561ac59c27b11365353e05a0d9e21fb79053fb2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "69665a7c708f03564198fdf74fd2ffacbf3dc4a98947baebd056d5f9cb12edd6", "generation_seconds_batch": 26.05157958494965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21394629776477814, "target_z": -0.2578124970940552, "ce": 5.998785495758057, "genuineness": 4.394378662109375, "identity": 0.6706824898719788, "hypothesis": "Piek 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_Emotional_Numbness/3e05877501abc0dc58e7a7111561ac59c27b11365353e05a0d9e21fb79053fb2.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": "3e184ea1348ad99c415f11192247876cf34f6f790d89d48d3aa8f953f184a87f", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bcc3ce2491e4bf4a34f93573a176ce6e5b1a210404248f156624fa7c21d4f282", "generation_seconds_batch": 25.357384431990795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5118224024772644, "target_z": 0.052001937172573634, "ce": 5.704906940460205, "genuineness": 4.846253395080566, "identity": 0.7590587139129639, "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_Emotional_Numbness/3e184ea1348ad99c415f11192247876cf34f6f790d89d48d3aa8f953f184a87f.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "3e2c7694ccd0ece48e58f6a837449367ce3397e83e72b3123176d0a014c18fd9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "be031c9e9ef06559bf63aeb7b19c6993fa506c0598689dc8b41dc01d733b0731", "generation_seconds_batch": 25.224670091993175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4183987081050873, "target_z": -0.04516600802716505, "ce": 5.855817794799805, "genuineness": 4.7458367347717285, "identity": 0.7992734909057617, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3e2c7694ccd0ece48e58f6a837449367ce3397e83e72b3123176d0a014c18fd9.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "3ea4f5b13a2ad16e50d964f5df59e0ccf2c0bc6ef3a9d0e8935a620570451e38", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "55a5b999e00d520b4676e298e40230b49a8866882e8cd8bb4a3dcec3eaf19f72", "generation_seconds_batch": 26.049036048934795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3256791830062866, "target_z": -0.1416015621367569, "ce": 5.855817794799805, "genuineness": 4.808597087860107, "identity": 0.7058802247047424, "hypothesis": "La porte 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_Emotional_Numbness/3ea4f5b13a2ad16e50d964f5df59e0ccf2c0bc6ef3a9d0e8935a620570451e38.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "3fbb89ca32781002695eb9c304cfabfbfd7991bd2ca442bf2b3348f9dda3ffdd", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "10a87f3713806017b624c4d7733389fb7677376acc8a7ac0129a1f819029b398", "generation_seconds_batch": 24.28032120305579, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9219008684158325, "target_z": 0.4785155981200102, "ce": 5.649308204650879, "genuineness": 4.607763767242432, "identity": 0.7739381790161133, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/3fbb89ca32781002695eb9c304cfabfbfd7991bd2ca442bf2b3348f9dda3ffdd.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": "40176cfa3186b569de80c43078ad26f3d07d30082db52f6b500df149662860c3", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7c038c9341976c3229b8a1caca0cca327795dd7806f069e83cfb5d2fd734f8c0", "generation_seconds_batch": 25.231431950000115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7303588390350342, "target_z": 0.27929691447241745, "ce": 5.919358730316162, "genuineness": 4.65797233581543, "identity": 0.6106352210044861, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik laste twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.08695652173913043, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/40176cfa3186b569de80c43078ad26f3d07d30082db52f6b500df149662860c3.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "4084fb60dd0076a92ef9d208a03bcca773bbe8a41c777a1f35d1fd7ecd4cfe2a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bd6c86618972c5a697863a346094428d3f24845c05c7eb5ce49515df79ece2cd", "generation_seconds_batch": 24.47970455500763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14822107553482056, "target_z": -0.3261718660400034, "ce": 6.165581703186035, "genuineness": 4.356721878051758, "identity": 0.37477076053619385, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/4084fb60dd0076a92ef9d208a03bcca773bbe8a41c777a1f35d1fd7ecd4cfe2a.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "40b61e20bd6fa6735787ab975db7d49e617e05c35e77eca71d91cc3e454ca709", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "69e35180182ea995b5c9660f7f05e34b7878199528681192beafdc272ac04143", "generation_seconds_batch": 18.133777698036283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20831269025802612, "target_z": -0.26367188928756213, "ce": 6.062326908111572, "genuineness": 4.406930446624756, "identity": 0.6218389868736267, "hypothesis": "Ik 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_Emotional_Numbness/40b61e20bd6fa6735787ab975db7d49e617e05c35e77eca71d91cc3e454ca709.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "40cda691f1ae06c7f0cb49b524d680c2f1dad9e80d2e440d5f71d3b8d9824728", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d8cb95dac35435ff51007a532d6b7016d7170594d58764c1d0ef4c818b58b78e", "generation_seconds_batch": 23.318626050953753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4200418293476105, "target_z": -0.04345703348999915, "ce": 5.982900142669678, "genuineness": 4.457139015197754, "identity": 0.6869924068450928, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/40cda691f1ae06c7f0cb49b524d680c2f1dad9e80d2e440d5f71d3b8d9824728.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "40db6eac406d7d79c51f006c266d503269c3203cd39d18c1735c3fff1b21e6f9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b91a9cdfc035b2f37ce588fe0c08186bb89390413285e0b066cb0363109a9d67", "generation_seconds_batch": 17.947392225032672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29093870520591736, "target_z": -0.17773437475783793, "ce": 5.831989288330078, "genuineness": 4.20609712600708, "identity": 0.2478141486644745, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are right.", "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_Emotional_Numbness/40db6eac406d7d79c51f006c266d503269c3203cd39d18c1735c3fff1b21e6f9.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "41601fea5d2d164ed7b126baa058c075bda9f08e25e8fd41872bf0a41377829b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3f189965a8e6d4bfc3e579eb7ed4bea2b481516ddf801d924af17143c2faef17", "generation_seconds_batch": 25.664538023993373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2101905643939972, "target_z": -0.26171875339026895, "ce": 5.7406487464904785, "genuineness": 4.758388519287109, "identity": 0.8342372179031372, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/41601fea5d2d164ed7b126baa058c075bda9f08e25e8fd41872bf0a41377829b.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "41c04f3a9b9829c75e6beefc5008b03488f11e5524e14c26bf639730dedcef00", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "79ce6aae7d19af4ac6e2b15aca01dd570a9fcd5daf39e0012c4504c730046764", "generation_seconds_batch": 17.10325859102886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3191066384315491, "target_z": -0.14843752227891044, "ce": 5.673136234283447, "genuineness": 4.482243061065674, "identity": 0.7801410555839539, "hypothesis": "La porte 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_Emotional_Numbness/41c04f3a9b9829c75e6beefc5008b03488f11e5524e14c26bf639730dedcef00.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "423a493565544d2d5bd2558000cbd1ca691e88e2440180bdc3fa6a8cbef7ee2f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "04a8cf87b6afe14bbff5963663961d18c56b4de157198988ec365959d57e8ca0", "generation_seconds_batch": 19.201657262048684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2101905643939972, "target_z": -0.26171875339026895, "ce": 5.760505676269531, "genuineness": 4.833701133728027, "identity": 0.7416098117828369, "hypothesis": "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_Emotional_Numbness/423a493565544d2d5bd2558000cbd1ca691e88e2440180bdc3fa6a8cbef7ee2f.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "427b8fd2e6b0b6c4317c3c22c1a75c11617a29c806de0d132d1dbcaa2efc6d42", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cceaee364870a50c00c5fd76203e0a8b589857ce77366b7de84ca1d06ebe4b5c", "generation_seconds_batch": 26.019981432007626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4331868886947632, "target_z": -0.029785144202437015, "ce": 6.0146708488464355, "genuineness": 4.6203155517578125, "identity": 0.6796251535415649, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/427b8fd2e6b0b6c4317c3c22c1a75c11617a29c806de0d132d1dbcaa2efc6d42.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "42f1c24d96d3baec54bb3737e7b67019c3c078fd6f28d9fcd17c7b16007f14a8", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "72eafafeeb22e10a4223c732c98888d312928e6e44acab4b00ccf200fa8d24fb", "generation_seconds_batch": 26.81849247601349, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38342350721359253, "target_z": -0.08154295101162837, "ce": 6.2767791748046875, "genuineness": 4.7834930419921875, "identity": 0.311962753534317, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/42f1c24d96d3baec54bb3737e7b67019c3c078fd6f28d9fcd17c7b16007f14a8.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": "42fb475fdc30cd8fcafa812cbfa1367c43656379314ac555b253d0bae7e8550a", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Your message arrived after I had left.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "938b2460185691790fab7ea8791cf261f6a89326ef911f3ce58553ff5dce8a40", "generation_seconds_batch": 19.386697283014655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7472596168518066, "target_z": 0.2968750445578209, "ce": 6.1020402908325195, "genuineness": 4.406930446624756, "identity": 0.35682302713394165, "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_Emotional_Numbness/42fb475fdc30cd8fcafa812cbfa1367c43656379314ac555b253d0bae7e8550a.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "d1b4bcfc427caa6add8d03c8d2cce36fe88c8a11e3213707a8f979a20819a273", "generation_seconds_batch": 16.465619422961026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13507601618766785, "target_z": -0.33984375532756556, "ce": 6.109982967376709, "genuineness": 4.293961524963379, "identity": 0.6776846051216125, "hypothesis": "De weg gaat linksaf na de brug. Loop verder. Tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "43a72d1d7dbfd64b1650325c9536016986c80ebf41850a367a1fc9b1bf149451", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3b95c680f7c4d84c88e35a478bc775ffcf87fb63fa21a8dec44ec9cd215abf6c", "generation_seconds_batch": 27.29841075197328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1801447570323944, "target_z": -0.2929687417664896, "ce": 5.9431867599487305, "genuineness": 4.6705241203308105, "identity": 0.6043510437011719, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what it 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_Emotional_Numbness/43a72d1d7dbfd64b1650325c9536016986c80ebf41850a367a1fc9b1bf149451.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "9c8275bb1e49f0fcfc050569a80b37d2dcc73f8434ffa7201b43aa731c15f0cb", "generation_seconds_batch": 18.483289603027515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04869428277015686, "target_z": -0.4296875106551311, "ce": 6.197352409362793, "genuineness": 4.570107460021973, "identity": 0.4991280436515808, "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_Emotional_Numbness/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "43db4fc66e09d18753ee64b43cdd5a497489e1ea7dd829ee427c8d231f920401", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a1e6d85e8c210d176aa5103100dbf32d4dadf141fb648ac4e743a592adb1f869", "generation_seconds_batch": 25.34271958505269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4942174553871155, "target_z": 0.03369141599702332, "ce": 5.681078910827637, "genuineness": 4.469690799713135, "identity": 0.5612480640411377, "hypothesis": "De deur 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_Emotional_Numbness/43db4fc66e09d18753ee64b43cdd5a497489e1ea7dd829ee427c8d231f920401.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "43f5ebf30c80aa12840b955e5e4224cd461a879be131931372a04d263fa7fbca", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5458fe657537a5b9007428ab2944d5b33d13643c8bcc5c24ee9087aa95006b9a", "generation_seconds_batch": 23.65710387402214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6712061166763306, "target_z": 0.21777345917350527, "ce": 6.062326908111572, "genuineness": 4.419482707977295, "identity": 0.5075644850730896, "hypothesis": "Ik 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_Emotional_Numbness/43f5ebf30c80aa12840b955e5e4224cd461a879be131931372a04d263fa7fbca.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "4492e7617b7bd548fd512b6f36d88a1049ce8a1b45db189dbbfd4494fbb87e97", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "91d4ae1661374a98aeb41e10416a3cc5471ae0fdee34349e1e261d383b56f41f", "generation_seconds_batch": 23.897109190002084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.289999783039093, "target_z": -0.17871092720811202, "ce": 6.0305562019348145, "genuineness": 4.469690799713135, "identity": 0.8794000148773193, "hypothesis": "La porte 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_Emotional_Numbness/4492e7617b7bd548fd512b6f36d88a1049ce8a1b45db189dbbfd4494fbb87e97.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "449f05d005fb0abe62b10a98a48b0d571d57380cb75903946751a8813de6f656", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "7a0809f9b17fe051abf5d17e542141f4887dc553602ee0f781fc3268884e7920", "generation_seconds_batch": 21.828531629987992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.364644855260849, "target_z": -0.10107421699432499, "ce": 5.450741291046143, "genuineness": 4.482243061065674, "identity": 0.6978816390037537, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/449f05d005fb0abe62b10a98a48b0d571d57380cb75903946751a8813de6f656.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "449f841806745a0a7ed667c9df77573fb0556ad26fae968cfbeaccb90fb0d8f1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d8ae5ce278209c8d206d60c279e557b0dc1f0d51be1a2a06b0b989d6fc447077", "generation_seconds_batch": 24.499420738080516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17263329029083252, "target_z": -0.3007812543589173, "ce": 6.062326908111572, "genuineness": 4.582659721374512, "identity": 0.6942957639694214, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/449f841806745a0a7ed667c9df77573fb0556ad26fae968cfbeaccb90fb0d8f1.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "44f0c0f82c93a34178b4961038e5c8eac5288e71cb14d1c022782b92e8a905cf", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ec46a0c36a2c680578c221694c7879e9b3080c9204ce599a115be00f0550955b", "generation_seconds_batch": 23.360577886924148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18953406810760498, "target_z": -0.2832031242735138, "ce": 5.855817794799805, "genuineness": 4.381826400756836, "identity": 0.6628475189208984, "hypothesis": "La porte 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_Emotional_Numbness/44f0c0f82c93a34178b4961038e5c8eac5288e71cb14d1c022782b92e8a905cf.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "44fa2256cd3daae08a138506ad16af12ef133e36f1324e0cdd7d98b0fb555596", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "70139858f82541de0e83e31a0daaa03c902c0b89be7357ca93368ec41a4ac51b", "generation_seconds_batch": 18.09223597997334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1388317346572876, "target_z": -0.3359375145297242, "ce": 5.927301406860352, "genuineness": 4.645420074462891, "identity": 0.8163375854492188, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/44fa2256cd3daae08a138506ad16af12ef133e36f1324e0cdd7d98b0fb555596.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "4530723b1d59abf1e84482b624e7c152193f120abfa4d44244e199d12fe52374", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 128, "seconds_generated": 10.24, "mp3_sha256": "cad696960d72eb54cabe51c5e962777066bbae3a21a0d85eb89468d796fe33fa", "generation_seconds_batch": 23.205603576032445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38342350721359253, "target_z": -0.08154295101162837, "ce": 6.157639026641846, "genuineness": 4.758388519287109, "identity": 0.7499833106994629, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/4530723b1d59abf1e84482b624e7c152193f120abfa4d44244e199d12fe52374.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "453a851b53d90884d51defe4f5beb763ca9fb1b986b3c1e75493840971fc9006", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c862b00dd68a4091455fdc01a7c12eeedce7f615a9603ffc34ffcbcb004746ef", "generation_seconds_batch": 25.18769460101612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5989083647727966, "target_z": 0.14257814558377596, "ce": 5.863759994506836, "genuineness": 4.457139015197754, "identity": 0.4953579902648926, "hypothesis": "Ik 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_Emotional_Numbness/453a851b53d90884d51defe4f5beb763ca9fb1b986b3c1e75493840971fc9006.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "45a86ad53cf4df0ba3d540b406cdc2bf202d580faf7ca97b1279c0d17848fbf9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "562be4a11c694052285edeceaf9983146e3e20a80201f69bd050613430885106", "generation_seconds_batch": 18.606724006938748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6759007573127747, "target_z": 0.2226562524216207, "ce": 6.054384231567383, "genuineness": 4.595211505889893, "identity": 0.58562171459198, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/45a86ad53cf4df0ba3d540b406cdc2bf202d580faf7ca97b1279c0d17848fbf9.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": "45dc95df3f2ab16e00ab9a8115cbef3bb7c8166946e8ac27dc7b375e6978c053", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c61a9fcd8a3e80644a24ea1e3ef88503b4d16ceefe95fe0381b9754839affa8", "generation_seconds_batch": 24.556372502003796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6233205795288086, "target_z": 0.1679687572648621, "ce": 5.982900142669678, "genuineness": 4.846253395080566, "identity": 0.7263942360877991, "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_Emotional_Numbness/45dc95df3f2ab16e00ab9a8115cbef3bb7c8166946e8ac27dc7b375e6978c053.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "01f67baec613c3e98062618b4d394ac87d359436b3c16d2aa96db63d38f21f85", "generation_seconds_batch": 17.65623405110091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07498437166213989, "target_z": -0.4023437630767518, "ce": 6.260893821716309, "genuineness": 3.8922953605651855, "identity": 0.6433464288711548, "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_Emotional_Numbness/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "46164d2100ef16d8b0cd7667a7cb792e7a3a6094b9ab3a1969dd76685011bd72", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5266da95cc5cba919932186420ac25d05f8f891c4c482973b7e3fd04c083fc26", "generation_seconds_batch": 23.87188117997721, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5308358073234558, "target_z": 0.07177736451539751, "ce": 5.756534099578857, "genuineness": 4.821148872375488, "identity": 0.6596969366073608, "hypothesis": "La porte 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_Emotional_Numbness/46164d2100ef16d8b0cd7667a7cb792e7a3a6094b9ab3a1969dd76685011bd72.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "4659072dbe1c607399edfc41bed6d12485428035bdeee75c45186f18694de748", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "41afccb2a0c5c4122aed11f6b661932f140fc2621ba88840360e9c63b1b69959", "generation_seconds_batch": 24.873002620064653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5322442054748535, "target_z": 0.07324220868918113, "ce": 5.6254801750183105, "genuineness": 4.532451152801514, "identity": 0.5478176474571228, "hypothesis": "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_Emotional_Numbness/4659072dbe1c607399edfc41bed6d12485428035bdeee75c45186f18694de748.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "46b3d305d3875836bb382e146ee06f0b84dc95aaf5634c882fe6d17a18a997cd", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ffb7a4d6608f2e281aa7e0fc2395f13f95b12275f7ba821fc37aba55b94144a2", "generation_seconds_batch": 25.851937155006453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15573251247406006, "target_z": -0.3183593844443207, "ce": 6.23706579208374, "genuineness": 4.758388519287109, "identity": 0.5513083338737488, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/46b3d305d3875836bb382e146ee06f0b84dc95aaf5634c882fe6d17a18a997cd.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "471cff7cb97c8a960bc159074045b2035b3ac572fb5f4f0d3304385b08b4b16a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "252f5524bbc85b218784c733d739706bcbcbc9c14faf30c721c5a390cda0c31f", "generation_seconds_batch": 17.775689291069284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1951676607131958, "target_z": -0.2773437475783793, "ce": 5.959072113037109, "genuineness": 4.494794845581055, "identity": 0.6364468932151794, "hypothesis": "De deur 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_Emotional_Numbness/471cff7cb97c8a960bc159074045b2035b3ac572fb5f4f0d3304385b08b4b16a.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": "47ac9fd40b3d50b8a1e567dbadc0b480d471de270088d85c37ae92549aa3848f", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "489c90608444548bf740beb91a7508ee4145f3267affbf8fe81848977af092a1", "generation_seconds_batch": 18.462995297973976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5416334867477417, "target_z": 0.08300779518541199, "ce": 5.327630043029785, "genuineness": 4.68307638168335, "identity": 0.8074259757995605, "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_Emotional_Numbness/47ac9fd40b3d50b8a1e567dbadc0b480d471de270088d85c37ae92549aa3848f.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "2abe19d5d9d1a98bb29e09ddcdcc8f7b5fcaf01461e773081222aba27fd08934", "generation_seconds_batch": 18.792211055057123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19141194224357605, "target_z": -0.2812499883762206, "ce": 6.046441555023193, "genuineness": 4.532451152801514, "identity": 0.7674573659896851, "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_Emotional_Numbness/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "47f59357243fe068e0092d3c15db556c53d00bb05504ccc6f4b4abaefbd92072", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5a97b3c2a0a2b28604fa761fa919d42da54d75dd4892dbf54805e8aaa65e60da", "generation_seconds_batch": 24.876118966960348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14258748292922974, "target_z": -0.3320312427351379, "ce": 6.284721851348877, "genuineness": 4.331617832183838, "identity": 0.5624316930770874, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/47f59357243fe068e0092d3c15db556c53d00bb05504ccc6f4b4abaefbd92072.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "489109a33b114070c592f78afe8352e93405b9a99da519e9f974eca8df2d29aa", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2a04c2cf8d3d05b8bb5584f78c0a42a4a1d23c0884ad9754a91d758c263a5f77", "generation_seconds_batch": 24.17088040302042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09000730514526367, "target_z": -0.3867187378918965, "ce": 5.911416053771973, "genuineness": 4.7081804275512695, "identity": 0.6642035245895386, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/489109a33b114070c592f78afe8352e93405b9a99da519e9f974eca8df2d29aa.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "4918bbc7486cc76a3cc9d337569b1a0f35e3965d3b6f98de8964adf651808450", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ee230101e87bcb179670e4eef33fdc397b18894bb5545f6e7379a36f159f9608", "generation_seconds_batch": 24.833278203033842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11066380143165588, "target_z": -0.3652343670086517, "ce": 6.173524379730225, "genuineness": 4.250029563903809, "identity": 0.33375680446624756, "hypothesis": "The 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_Emotional_Numbness/4918bbc7486cc76a3cc9d337569b1a0f35e3965d3b6f98de8964adf651808450.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": "497244fb3f38a296add1df01876380ebe01979d49f0446aeacacfd0322b4244a", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f3627d9c158a2baded85af819dc8160992c78400f67f03796e8a5f46e560bc6c", "generation_seconds_batch": 25.67379918100778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5702708959579468, "target_z": 0.112792939387849, "ce": 5.609594821929932, "genuineness": 4.758388519287109, "identity": 0.7402439713478088, "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_Emotional_Numbness/497244fb3f38a296add1df01876380ebe01979d49f0446aeacacfd0322b4244a.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "49bd3c27850a3ffd328b1989e5ad0321f000f7ddb46a465ec7ea6e58116d9f6f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b1542a7eb61f8a4103223785bc330c953779c3701f48c69c4ec33af6cbe04dc", "generation_seconds_batch": 24.873002620064653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34586620330810547, "target_z": -0.12060548297702162, "ce": 5.593709468841553, "genuineness": 4.6956281661987305, "identity": 0.5593781471252441, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/49bd3c27850a3ffd328b1989e5ad0321f000f7ddb46a465ec7ea6e58116d9f6f.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "49d328a55575631bca657aaaf8229dfb8ba8feef2ba53e004b9b421610d43af0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "317af4811ccf4fd39c343e79a9cf62d710adb22a5e0a0b6deba47d2594e91187", "generation_seconds_batch": 25.914560534991324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38013723492622375, "target_z": -0.08496093108270514, "ce": 5.879645347595215, "genuineness": 4.570107460021973, "identity": 0.6460676193237305, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/49d328a55575631bca657aaaf8229dfb8ba8feef2ba53e004b9b421610d43af0.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "08f6a520ce3fc8e9d594f1c7cffba00adf2be057f7d08da92017fd94cdb83d16", "generation_seconds_batch": 19.828906620037742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08625155687332153, "target_z": -0.3906250096864828, "ce": 6.221180438995361, "genuineness": 4.2374773025512695, "identity": 0.7442127466201782, "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_Emotional_Numbness/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "49dfcaa43394c0ec20897b462d02876bed0beecab704972e8110b559ff1c82f3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9a785f7fe04bb8ec9aafb43ded2f6852226ba23ba257157ea2bae59a239cb322", "generation_seconds_batch": 24.738524249987677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2571371793746948, "target_z": -0.2128906039318999, "ce": 5.990842819213867, "genuineness": 4.570107460021973, "identity": 0.7115542888641357, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/49dfcaa43394c0ec20897b462d02876bed0beecab704972e8110b559ff1c82f3.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "4b3fb50af226dad472c131c65fecc0ad5c5c0ea0b68c571cb938a540ba54202b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4482cdc2d3cbc56827b496a7e255cad7b04fb0e9b4254eb0b95ae851547aec5d", "generation_seconds_batch": 25.55564652895555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 6.24500846862793, "genuineness": 4.821148872375488, "identity": 0.6053711771965027, "hypothesis": "La porte est encore 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_Emotional_Numbness/4b3fb50af226dad472c131c65fecc0ad5c5c0ea0b68c571cb938a540ba54202b.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": "4b6ccbcbf1c72da31a7f4c2b44efd8e4ad1601d3385d85973a8676f4d66acb91", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I wrote the number on the envelope.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "0cc3ea190004c0aa5615ddb38c75e111f7532c9288435456da05721b4a8e5907", "generation_seconds_batch": 18.50217580702156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42802274227142334, "target_z": -0.03515626017080695, "ce": 5.609594821929932, "genuineness": 4.369274139404297, "identity": 0.3638613224029541, "hypothesis": "I wrote the number on the envelope. Read it carefully. I checked the last two digits. Call me when you have a moment.", "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_Emotional_Numbness/4b6ccbcbf1c72da31a7f4c2b44efd8e4ad1601d3385d85973a8676f4d66acb91.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "4c011bdae1fb4fbfed08a52e45dcb4641dd6c0ef1def84f63d936ba8631e78f6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2e7c6758fe570a7e0ab7f1ec701bc7cf9e054e7b048fcbad956f44e813578434", "generation_seconds_batch": 18.554787694942206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6993740797042847, "target_z": 0.24707034264917774, "ce": 5.8875885009765625, "genuineness": 4.833701133728027, "identity": 0.5865845084190369, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/4c011bdae1fb4fbfed08a52e45dcb4641dd6c0ef1def84f63d936ba8631e78f6.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "4c58abc2582a9ed55bc27d98dba746303a20e4372b5e37a8731ca1869a0845c0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6bf614e88ae203f7fe721e651002bf4c951c636e73aa8586dc3200d6f727fbd4", "generation_seconds_batch": 22.217980609973893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29375550150871277, "target_z": -0.1748046864102707, "ce": 5.77639102935791, "genuineness": 4.3504462242126465, "identity": 0.5915037393569946, "hypothesis": "De deur 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_Emotional_Numbness/4c58abc2582a9ed55bc27d98dba746303a20e4372b5e37a8731ca1869a0845c0.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "4c6dc58b22451778cb63d30ee19f51a546bde8310c34edce2b3536045f1c3b45", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "372d7f8c67e5a7382aec64f02ac47ab031039e327bc0e9dba1a15b7f5e910403", "generation_seconds_batch": 22.774602573015727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19892337918281555, "target_z": -0.27343750678053796, "ce": 5.998785495758057, "genuineness": 4.469690799713135, "identity": 0.8022265434265137, "hypothesis": "La porte 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_Emotional_Numbness/4c6dc58b22451778cb63d30ee19f51a546bde8310c34edce2b3536045f1c3b45.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "4cb8c4f156587af43b7217282a4ced6ec7902dec1722c449001bbc8512f904ca", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "13747b00596473ccbacecd59b1ee4c543d9b3d86561ccf043fd6330a2361df23", "generation_seconds_batch": 26.325569272972643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26558753848075867, "target_z": -0.20410156988594313, "ce": 6.284721851348877, "genuineness": 4.570107460021973, "identity": 0.5333961844444275, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/4cb8c4f156587af43b7217282a4ced6ec7902dec1722c449001bbc8512f904ca.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": "4cbc98e64acbab7dcd0c3ebfc5e767ef2bf43c0fcf72fd3a438af1b9722d8f4c", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The keys are on the kitchen table.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b396c2b505c093e9a6c12747e43f365b2d32ce6d37f6ee3943bae3af41fd8862", "generation_seconds_batch": 24.261023254017346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15385466814041138, "target_z": -0.3203124893448689, "ce": 5.895530700683594, "genuineness": 4.356721878051758, "identity": 0.3291560411453247, "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_Emotional_Numbness/4cbc98e64acbab7dcd0c3ebfc5e767ef2bf43c0fcf72fd3a438af1b9722d8f4c.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "4cef771d532cc9f2e9943f0fb720efe4d394b8c96f40c1b7d8cfe8240fa9adb4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0e91004fe69048920a87018c04ff8419d5cb54fdd73ace4a0c180e6fa8101d2f", "generation_seconds_batch": 22.873861578991637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36370593309402466, "target_z": -0.10205076944459908, "ce": 6.054384231567383, "genuineness": 4.6203155517578125, "identity": 0.7083105444908142, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/4cef771d532cc9f2e9943f0fb720efe4d394b8c96f40c1b7d8cfe8240fa9adb4.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "4e672afea939b845fd143bcaeb352e0612e607b68d5368d551df08ca3d391165", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d2484b422e75d72387b04f310ccb1180176766cafadebb5adaac050ea5ef0b21", "generation_seconds_batch": 23.128716851002537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13695389032363892, "target_z": -0.3378906194302724, "ce": 6.133810997009277, "genuineness": 4.457139015197754, "identity": 0.5048367381095886, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/4e672afea939b845fd143bcaeb352e0612e607b68d5368d551df08ca3d391165.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "4e921e152c7af52d0c41756048c3487a83da78927b09c27b73b82b4462b42389", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3085d04e255856932a55e64ea1f4c676fa39bb808624ba9de0172e5a50cc15e6", "generation_seconds_batch": 25.756641801912338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2890608310699463, "target_z": -0.17968751065513108, "ce": 5.998785495758057, "genuineness": 4.432034492492676, "identity": 0.7286406755447388, "hypothesis": "De deur 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_Emotional_Numbness/4e921e152c7af52d0c41756048c3487a83da78927b09c27b73b82b4462b42389.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "4ee48aa1e77d77d7541c81e4ea6b56045a74fdb5fa9e977e4f188fd75b632dda", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7697c846b5ff05fe632730fdf0a1c9a6e114aa69f39ef172b35a4934d42552b2", "generation_seconds_batch": 20.607228875043802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0064047574996948, "target_z": 0.5664062485470276, "ce": 5.502368927001953, "genuineness": 4.808597087860107, "identity": 0.7872755527496338, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/4ee48aa1e77d77d7541c81e4ea6b56045a74fdb5fa9e977e4f188fd75b632dda.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": "4ef87a5add92312740edf7dc3bda72ce4f1dfdc6b3f03db3d83ea89ed0d19cb8", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "273947f8d8fc4c425e65e3a8eb5765696f3f07b9cb438a2137b874e502e7dcbf", "generation_seconds_batch": 17.451551003032364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4653452932834625, "target_z": 0.0036621104344590565, "ce": 5.796247482299805, "genuineness": 4.8588056564331055, "identity": 0.7658515572547913, "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_Emotional_Numbness/4ef87a5add92312740edf7dc3bda72ce4f1dfdc6b3f03db3d83ea89ed0d19cb8.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "4f1c87d08b03c7c475958889c959652c2781760a4f7fedbaf0104fdf454ce535", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "31413c04c03df318d9f1637e70c4370fba29faa9ee19c70905a3a39ef140d607", "generation_seconds_batch": 25.306314384914003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3510303497314453, "target_z": -0.11523436700865168, "ce": 5.692992687225342, "genuineness": 4.532451152801514, "identity": 0.7342617511749268, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/4f1c87d08b03c7c475958889c959652c2781760a4f7fedbaf0104fdf454ce535.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": "4f492fab63c1f0135a9ddb8c154c28255edd6c97a94546acd05a7892e67fcd55", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b59222018cb55c5f756a298a3d548a3b51cc3cd3ddbdb34d65a7164b19263c3", "generation_seconds_batch": 26.28667589998804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7472596168518066, "target_z": 0.2968750445578209, "ce": 6.117925643920898, "genuineness": 4.545003414154053, "identity": 0.572708249092102, "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_Emotional_Numbness/4f492fab63c1f0135a9ddb8c154c28255edd6c97a94546acd05a7892e67fcd55.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "4fb4944c94d0a3bf73a6fe3b03c33bbc6450e8bb35a335b4cfca843d39537fa5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "785fcf6613a54aa4abb45f3cfc3726f0566572252d0db6395b1208c854a5aaf6", "generation_seconds_batch": 18.518793233088218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3069005608558655, "target_z": -0.16113279712270856, "ce": 6.022613525390625, "genuineness": 4.595211505889893, "identity": 0.24441075325012207, "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_Emotional_Numbness/4fb4944c94d0a3bf73a6fe3b03c33bbc6450e8bb35a335b4cfca843d39537fa5.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "4ffade3357eabf3e6fb84f20bc6acd267b316a708fab7d6af5cea4f5edd234d1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "28fb3e4c476697f18ab6bca2a9ed3e398f4b9fc6ad74c1c9c8771ad6ed050101", "generation_seconds_batch": 16.853723019943573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13507601618766785, "target_z": -0.33984375532756556, "ce": 6.221180438995361, "genuineness": 4.149612903594971, "identity": 0.3058059811592102, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/4ffade3357eabf3e6fb84f20bc6acd267b316a708fab7d6af5cea4f5edd234d1.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "501a49429162f5679398e676187fdc23f6badd41cc4303ddd054ecad42399d01", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78bebe267bab8f7ba703df8a2ae100800c37a7a37fc32012a4f65b542dd10439", "generation_seconds_batch": 25.252448305953294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20080125331878662, "target_z": -0.2714843708832448, "ce": 6.086154937744141, "genuineness": 4.394378662109375, "identity": 0.36077016592025757, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/501a49429162f5679398e676187fdc23f6badd41cc4303ddd054ecad42399d01.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "5069e36d39b0393ffa1f24ec1f46209a77777180cfae9de3c31635862cf9af4d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2f5a7106efc1f9d05a1fda788e70bc344d66d1b39d8ce26c44e6d6c184f9c37a", "generation_seconds_batch": 23.90075221308507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5019636154174805, "target_z": 0.04174802795608828, "ce": 5.728734970092773, "genuineness": 4.7332844734191895, "identity": 0.7615454196929932, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/5069e36d39b0393ffa1f24ec1f46209a77777180cfae9de3c31635862cf9af4d.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "50bdfcf1c489663e9cb6ff962065934a7af9ae4d23a377a7b47f72d0918a4908", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6b44784965ad2733c9e57167067a86d1591d5c9d3fc272efd2860f30956eab3c", "generation_seconds_batch": 25.133542594034225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10503020882606506, "target_z": -0.37109374370378617, "ce": 6.078212261199951, "genuineness": 4.6203155517578125, "identity": 0.8432352542877197, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/50bdfcf1c489663e9cb6ff962065934a7af9ae4d23a377a7b47f72d0918a4908.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "511f14a8070f180b040368ab42e902881415dc20a93cdb44b0e8ab1112a2f8de", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "500d58c97c9daec451145dc777aa387a809880ff4d4bf95b50b0845a5a65646d", "generation_seconds_batch": 23.65710387402214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42497122287750244, "target_z": -0.03833007888175647, "ce": 5.935244083404541, "genuineness": 4.457139015197754, "identity": 0.6197777390480042, "hypothesis": "Ik 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_Emotional_Numbness/511f14a8070f180b040368ab42e902881415dc20a93cdb44b0e8ab1112a2f8de.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "51dfc35e4eaf6fe44343d20e575aa629351c5451281b0f42551f0f60dcd42458", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d04977125140654fc122c2b3cd15ff72bcbcc786cad07394198961dfcd5ee545", "generation_seconds_batch": 18.002406697021797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3914044201374054, "target_z": -0.07324217769243616, "ce": 5.863759994506836, "genuineness": 4.394378662109375, "identity": 0.4018036723136902, "hypothesis": "De deur 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_Emotional_Numbness/51dfc35e4eaf6fe44343d20e575aa629351c5451281b0f42551f0f60dcd42458.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "52b53157bfba909e13ecab15ef77ad621866e5a07925e1ce248f8771ab647a87", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d36b55089139bcef83caf631ab42ee12d620a04a2ef7180aa859dea812a0daf1", "generation_seconds_batch": 24.207531283958815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16136610507965088, "target_z": -0.31250000774918624, "ce": 6.0305562019348145, "genuineness": 4.469690799713135, "identity": 0.6707624197006226, "hypothesis": "Ik 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_Emotional_Numbness/52b53157bfba909e13ecab15ef77ad621866e5a07925e1ce248f8771ab647a87.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "532d643fd989a35f6cecb7fd1612f027b8238074dc8930c625ac66bc0cc19506", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "890d0716ab6f1fb77227cc1d8c250a1f73c5f5a59c9af49afede06df3737dd34", "generation_seconds_batch": 26.325081994989887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3881181478500366, "target_z": -0.07666015776351294, "ce": 5.760505676269531, "genuineness": 4.6705241203308105, "identity": 0.6401799917221069, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/532d643fd989a35f6cecb7fd1612f027b8238074dc8930c625ac66bc0cc19506.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "534a6cc24c6b59283222e5c63ded2a88b27480945910f5aa2b195d4953c5554a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3e92538aa548eb6ce98d2ff2e1706f8b9c915a5583360a5e2f50ea60517229e6", "generation_seconds_batch": 18.319008890073746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.314411997795105, "target_z": -0.15332031552702588, "ce": 6.0146708488464355, "genuineness": 4.821148872375488, "identity": 0.8301419019699097, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/534a6cc24c6b59283222e5c63ded2a88b27480945910f5aa2b195d4953c5554a.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "537e7a435743b2688fc85a09876902052c4bca2aa4fb9fe0fc3d733df9aebc4b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d2dc778699fad8d9433edf7a97ddd2c5ede98b1f2bc3a181e7f4feca63022a21", "generation_seconds_batch": 21.175825201091357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5057193636894226, "target_z": 0.04565429975067458, "ce": 5.530168056488037, "genuineness": 4.720732688903809, "identity": 0.6069666147232056, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/537e7a435743b2688fc85a09876902052c4bca2aa4fb9fe0fc3d733df9aebc4b.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "539022c6b9b0dec1a815b015c57b7a4433addcf14bab6435636a5647473ec72d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2ebd0fc6fa991cf15cb2d5431bf5f2fa3e0e917b69165556d1ba1b996960a66b", "generation_seconds_batch": 17.501073242048733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4639368951320648, "target_z": 0.002197266260675434, "ce": 5.935244083404541, "genuineness": 4.557555198669434, "identity": 0.6403814554214478, "hypothesis": "Ik 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_Emotional_Numbness/539022c6b9b0dec1a815b015c57b7a4433addcf14bab6435636a5647473ec72d.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "53a1b0801750916e8ef414444bf28f9ffe749ec245ab6e5c935200153cfce635", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "becfd067053e6cfd0aba5bf79ff391f9c489d5a7ebf7abd16607f6eb5fe0f656", "generation_seconds_batch": 23.860751954023726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05057215690612793, "target_z": -0.42773437475783793, "ce": 6.435632705688477, "genuineness": 4.306513786315918, "identity": 0.6369920372962952, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/53a1b0801750916e8ef414444bf28f9ffe749ec245ab6e5c935200153cfce635.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "d1e90342c486bd829dc12c37ff5603281f2069da147b78ec912dc18cc63cdfb2", "generation_seconds_batch": 17.65623405110091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09000730514526367, "target_z": -0.3867187378918965, "ce": 6.157639026641846, "genuineness": 3.9173994064331055, "identity": 0.7131667137145996, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.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": "5489ac9e47ac1c2be788afb1bc2b963a94af7cd9cdd9fad826f19f7d0f54c0e2", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "32adadc97ebcf97f8708d87f79221aea9ccb14dc58e6051e607dbd2b0639dfc8", "generation_seconds_batch": 25.137927028001286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8261298537254333, "target_z": 0.37890625629621383, "ce": 5.879645347595215, "genuineness": 4.482243061065674, "identity": 0.6140925288200378, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5489ac9e47ac1c2be788afb1bc2b963a94af7cd9cdd9fad826f19f7d0f54c0e2.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "54f167cd61044d95962f8396da8947bb8f1d28cc2edab39987cfc6b7b407a537", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fbcd15fb390481f8ab04009ec3cd274c8a3d3e6b4ab970d41393dc3c2e3e9096", "generation_seconds_batch": 22.53731990302913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1519767940044403, "target_z": -0.32226562524216207, "ce": 6.23706579208374, "genuineness": 4.457139015197754, "identity": 0.3659377694129944, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/54f167cd61044d95962f8396da8947bb8f1d28cc2edab39987cfc6b7b407a537.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "54f7a6a4d0a6899ea588d566c01c8cb52d0b4b98d82781aa2ff91d5874a1cf1c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bb646dc2497a38fc1db0ad85f88c0ca8e65753084030a5e0826a36e4c4626482", "generation_seconds_batch": 23.8420006360393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21394629776477814, "target_z": -0.2578124970940552, "ce": 6.173524379730225, "genuineness": 4.720732688903809, "identity": 0.4329214096069336, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/54f7a6a4d0a6899ea588d566c01c8cb52d0b4b98d82781aa2ff91d5874a1cf1c.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": "5518ec15ccdd3696e1adf78cacf88e9450202a8fd0cc722d5e4fd43a2c3e4cff", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b95eaec9d692f09f2d9b8b9b9e9c501a50a893a83d71cf168ffeead6db2fb4d", "generation_seconds_batch": 16.90348296496086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.427083820104599, "target_z": -0.036132812621081034, "ce": 5.8875885009765625, "genuineness": 4.65797233581543, "identity": 0.6511696577072144, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5518ec15ccdd3696e1adf78cacf88e9450202a8fd0cc722d5e4fd43a2c3e4cff.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "55ad482ea2578378f86b5a6e0998dc1bb9024b1c8ae54dc7260a2ff1611d7882", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "08c4748138c7f74258e7191593738754ed949e29595775b394d2b7ff7f877248", "generation_seconds_batch": 23.601214546943083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1519767940044403, "target_z": -0.32226562524216207, "ce": 6.109982967376709, "genuineness": 4.3881025314331055, "identity": 0.5638763308525085, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het Adi, naast het oude raam. We kunnen er samen in kijken.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/55ad482ea2578378f86b5a6e0998dc1bb9024b1c8ae54dc7260a2ff1611d7882.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "55ae3acb3cb55d7c963e5a709aba5452266eeb9a5deb98716f3fe091f07b51c6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b56c34a06f74b8f10116589a8e0600f8e19d0b1e3530f6a6e8dc3c8db5ce5ec9", "generation_seconds_batch": 17.501073242048733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4712722897529602, "target_z": 0.009826650083821397, "ce": 5.982900142669678, "genuineness": 4.432034492492676, "identity": 0.5554172396659851, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen aan 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_Emotional_Numbness/55ae3acb3cb55d7c963e5a709aba5452266eeb9a5deb98716f3fe091f07b51c6.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "55c70fa2da01b82ddf70171efd72ff1ca8417137df93abc2aa3123291c04dc22", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3642e297956252fd85b126b135b974a2e41daa3b535475f5de1f9537fb00ba80", "generation_seconds_batch": 25.90426329395268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25244247913360596, "target_z": -0.21777345917350527, "ce": 5.903473377227783, "genuineness": 4.457139015197754, "identity": 0.21034863591194153, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/55c70fa2da01b82ddf70171efd72ff1ca8417137df93abc2aa3123291c04dc22.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "56727513f63c5faeac04a86713c5de21a4be55e9806b863c1c25cd410c85c609", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "574c3b9235623558f504363b469ce5cbc2523468c4c41806ab6221a3102998c4", "generation_seconds_batch": 18.354109765030444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38624030351638794, "target_z": -0.07861326266406111, "ce": 6.348263263702393, "genuineness": 4.6203155517578125, "identity": 0.19425371289253235, "hypothesis": "The 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_Emotional_Numbness/56727513f63c5faeac04a86713c5de21a4be55e9806b863c1c25cd410c85c609.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "5680d22b120e57d2bb6ec2a9d556f7924aa06e80b6e5ccecfe420dc2169acd65", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7405185139db698242cb633fb97819b9ec6cb86ac63ee29dfb8e74dac557f45a", "generation_seconds_batch": 16.05060944892466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22145774960517883, "target_z": -0.25, "ce": 6.165581703186035, "genuineness": 4.6956281661987305, "identity": 0.7480674386024475, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5680d22b120e57d2bb6ec2a9d556f7924aa06e80b6e5ccecfe420dc2169acd65.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "56dafd87b6dcea83bed7c0d08ef8d4e9ff8b6a9fa32aaa8ab627542164070a66", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6ed61f93575c58246f22833903eb8cd82e28de5d495250e97a452c53ed8e610e", "generation_seconds_batch": 25.48772083001677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 6.086154937744141, "genuineness": 4.808597087860107, "identity": 0.8192295432090759, "hypothesis": "J'ai trouvé la ta 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_Emotional_Numbness/56dafd87b6dcea83bed7c0d08ef8d4e9ff8b6a9fa32aaa8ab627542164070a66.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "570f06a424304970aa73934dd6c86267e77f5a0d751e166c29147a1731278bb3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "56bc61312453b9cb88accf6b9bf29f9b6b5cee8b3176e560a25a780f05eb7da7", "generation_seconds_batch": 25.689706429024227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0251834392547607, "target_z": 0.5859375455264692, "ce": 5.297844886779785, "genuineness": 4.6203155517578125, "identity": 0.6119602918624878, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/570f06a424304970aa73934dd6c86267e77f5a0d751e166c29147a1731278bb3.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "57de178f9a9ae444dc0d4f52902db454daea1f6c5b5de208ae8fcfc3ac3b42fc", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8413bdcf5f095bac951b2114b0172ac8cb9da601834e37d6bf6c0bc285aeee0d", "generation_seconds_batch": 20.3815203019185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47050940990448, "target_z": 0.009033195406084016, "ce": 5.613565921783447, "genuineness": 4.7834930419921875, "identity": 0.717961311340332, "hypothesis": "La porte 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_Emotional_Numbness/57de178f9a9ae444dc0d4f52902db454daea1f6c5b5de208ae8fcfc3ac3b42fc.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": "58c7c4a9f1bf77ec26fdf20084b4356858ade65e8aa01dbb34285a1dc6d679b3", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "45b8c353b17484e210edc690d26db8b213ef3a2db11966dcc0bd602b074e9dc4", "generation_seconds_batch": 18.36375128303189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.876832127571106, "target_z": 0.4316405845589343, "ce": 5.673136234283447, "genuineness": 4.7081804275512695, "identity": 0.7513842582702637, "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_Emotional_Numbness/58c7c4a9f1bf77ec26fdf20084b4356858ade65e8aa01dbb34285a1dc6d679b3.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "5903d3c7b4208d9856015d9e6b261e917d793a53161a1c55f7e5345d2ee9e8c2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "660144687e4eb1d7c7c83910efedc45a67af29c1855a11d2bd343b3ec6766494", "generation_seconds_batch": 24.29099760495592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4694531261920929, "target_z": 0.007934577774118785, "ce": 5.395142555236816, "genuineness": 4.758388519287109, "identity": 0.6198078989982605, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5903d3c7b4208d9856015d9e6b261e917d793a53161a1c55f7e5345d2ee9e8c2.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "5946c2a1d20af1809fa25e42ce8b82f3e29c016096c050a981e1016b7adeef2a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "94b47733ba1782e70bb3b65dc3703e597b86a25f877e78593eb35f9f2089296e", "generation_seconds_batch": 25.71544219891075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05057215690612793, "target_z": -0.42773437475783793, "ce": 6.308549880981445, "genuineness": 4.482243061065674, "identity": 0.2920968234539032, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5946c2a1d20af1809fa25e42ce8b82f3e29c016096c050a981e1016b7adeef2a.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "59d8e0071263d83dedcef63585401ea17a2216ab01f830e30990b8f6ba251340", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f757b42712b6c27967d315573702c6fae1004e19ebeaac9c4af854e88fda657", "generation_seconds_batch": 24.819998366991058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.314411997795105, "target_z": -0.15332031552702588, "ce": 5.935244083404541, "genuineness": 4.582659721374512, "identity": 0.506064772605896, "hypothesis": "De deur 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_Emotional_Numbness/59d8e0071263d83dedcef63585401ea17a2216ab01f830e30990b8f6ba251340.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "5a3bf31673a603dcd5e3141242d6938457c13a43076a973d2d5a402d5a514450", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e7a0139a5abb5ef2aeaef2ae518327ee66e267eb680a343a62f4de112486cc8d", "generation_seconds_batch": 21.40593752101995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6449159979820251, "target_z": 0.190429680598381, "ce": 6.0305562019348145, "genuineness": 4.770940780639648, "identity": 0.7021549344062805, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5a3bf31673a603dcd5e3141242d6938457c13a43076a973d2d5a402d5a514450.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "5abd79b4812b4164c6e440633188c0c8a387bae73d381bdc0988a409e08d3202", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b6a107187ce1df3eac92d8881d6dee8504e4c34ca762fbdce1d2a764db4853a4", "generation_seconds_batch": 19.937948689912446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5622900128364563, "target_z": 0.10449219706540176, "ce": 5.959072113037109, "genuineness": 4.632867813110352, "identity": 0.6904592514038086, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5abd79b4812b4164c6e440633188c0c8a387bae73d381bdc0988a409e08d3202.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": "5ac2c007615bc9e5d59f9dcce15d027e42e9cd1de56998e3606654b1773975c9", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Someone moved the little blue chair.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "767f4a84103b73fe4a94ed7d8568aca2c204182c0383fcb3cb05a4f9ddbb1e76", "generation_seconds_batch": 28.149077885085717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4345952868461609, "target_z": -0.028320300028653392, "ce": 6.2767791748046875, "genuineness": 4.632867813110352, "identity": 0.3691490590572357, "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_Emotional_Numbness/5ac2c007615bc9e5d59f9dcce15d027e42e9cd1de56998e3606654b1773975c9.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "5af5405958ef318b38ab66fa0f94bbc2ff58047c058f9125fcb08fb1d91d3d0b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ab9276cc5ddaa181e18b14ac133de37b8cd3c7d9262ebb36439a3ee678af8b4d", "generation_seconds_batch": 19.631717980024405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3425799608230591, "target_z": -0.12402343205135342, "ce": 5.895530700683594, "genuineness": 4.6956281661987305, "identity": 0.6407308578491211, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5af5405958ef318b38ab66fa0f94bbc2ff58047c058f9125fcb08fb1d91d3d0b.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "5b285b46cc8af967bf9e8fc3f211de594708f1e8d94985833a4ec6af8d1b9d60", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b994d86ffe299a2d21f08ad5bbb0b25fb089f5a40ca9dae17122f3fc3a56976", "generation_seconds_batch": 24.354019216028973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14070960879325867, "target_z": -0.3339843786324311, "ce": 5.982900142669678, "genuineness": 4.557555198669434, "identity": 0.7803324460983276, "hypothesis": "La porte 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_Emotional_Numbness/5b285b46cc8af967bf9e8fc3f211de594708f1e8d94985833a4ec6af8d1b9d60.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "5b690c1e98debb89b066ee9ec56261f4c5375b992488d0469d32370b1288a427", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a7c5d0b461c0a6e8101e2f568283f96d5efb2e36f24edf36fe82be9a61ad1258", "generation_seconds_batch": 25.63908661797177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31347307562828064, "target_z": -0.15429686797729997, "ce": 5.824047088623047, "genuineness": 4.770940780639648, "identity": 0.7792455554008484, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/5b690c1e98debb89b066ee9ec56261f4c5375b992488d0469d32370b1288a427.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "5ba8d438e72426b9a1af3d346149e34c01a89c379f2fb9e7a28d0fbc18c27060", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9397678d3a8524293333f6c4f701370db32d29095cde9a15aac1373bda4b1932", "generation_seconds_batch": 25.352902862941846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 6.23706579208374, "genuineness": 4.7834930419921875, "identity": 0.5898908972740173, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5ba8d438e72426b9a1af3d346149e34c01a89c379f2fb9e7a28d0fbc18c27060.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "5c8327213a250571194bc62fd8f9c6596cd77f4fbdf666c1dd1c881307091e9d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "64a5b7d81c6b5048573686892f9a1bf6624df643dc62ef38b951ee0a734fd8e2", "generation_seconds_batch": 23.079374531982467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2383585274219513, "target_z": -0.23242186991459654, "ce": 6.054384231567383, "genuineness": 4.557555198669434, "identity": 0.5845998525619507, "hypothesis": "De deur 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_Emotional_Numbness/5c8327213a250571194bc62fd8f9c6596cd77f4fbdf666c1dd1c881307091e9d.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "5caaa8e349e862ae088dccfcc288702abef2d8bb40c0698fa334c115dcb1403e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "291b2f195be758b6ee7135a901e111effba6d6933bda59ba536a0e146a508cc9", "generation_seconds_batch": 25.85750816296786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49938157200813293, "target_z": 0.03906250096864828, "ce": 5.792276382446289, "genuineness": 4.833701133728027, "identity": 0.5886697769165039, "hypothesis": "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_Emotional_Numbness/5caaa8e349e862ae088dccfcc288702abef2d8bb40c0698fa334c115dcb1403e.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "5cc9119939b3fd3df215f97a602558c4681e1fc01b534464fd7deb3370f0ce00", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "68d0f60a48d61d06840328857935bee5140ef0cf2705da4a70b818d7c3f06aa2", "generation_seconds_batch": 24.88019399798941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2233356088399887, "target_z": -0.24804687960107932, "ce": 6.062326908111572, "genuineness": 4.833701133728027, "identity": 0.5426210165023804, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5cc9119939b3fd3df215f97a602558c4681e1fc01b534464fd7deb3370f0ce00.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "5d08a9eafb7c26c2b274d9796680ec2a96694af8d51881403fb9c3c9d422d534", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "d2d46f5bd1abfa7490834ad2be205318b267a95997d938ccaa57a4888befa4a4", "generation_seconds_batch": 25.44388528598938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30032801628112793, "target_z": -0.1679687572648621, "ce": 6.141753673553467, "genuineness": 4.68307638168335, "identity": 0.6422019600868225, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5d08a9eafb7c26c2b274d9796680ec2a96694af8d51881403fb9c3c9d422d534.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "5d8ea20cd77134fd80fef5d1cb36906db2c617eab1066b91ff03071a9898b6d0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1f6edd1ef47422008054977d8a2c7914dbd891ed9c9784409bbbe69c2b7194d0", "generation_seconds_batch": 29.09519086498767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5768434405326843, "target_z": 0.11962889953000255, "ce": 5.506340026855469, "genuineness": 4.65797233581543, "identity": 0.5597385168075562, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5d8ea20cd77134fd80fef5d1cb36906db2c617eab1066b91ff03071a9898b6d0.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "5dd477f128637a879aea2e41c7dfc39621f00cfb80f8d372028cdcf2b79cfc2c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "41d1924309346f58fb51151f925d554773921595fe26e9d17cb45f93875a4158", "generation_seconds_batch": 17.058613940957002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5754350423812866, "target_z": 0.11816405535621893, "ce": 6.1020402908325195, "genuineness": 4.632867813110352, "identity": 0.6040719747543335, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5dd477f128637a879aea2e41c7dfc39621f00cfb80f8d372028cdcf2b79cfc2c.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "7f49b154db98a664abd38fc4fc8b0ff0dd2e547c0b7b7b9a12a8b0667880a35c", "generation_seconds_batch": 19.989352807984687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3970380127429962, "target_z": -0.06738280099730166, "ce": 6.205295085906982, "genuineness": 4.432034492492676, "identity": 0.8648244142532349, "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_Emotional_Numbness/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "5e1fc0b2a67824247dbdc75b9fbb95820bd3f9088000495d7502bf2ef69a9f4b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a5aa28f950fec6a8ba4ca693a0760bf5d589de4927864a1c41092f4fc5a908b", "generation_seconds_batch": 23.65951520006638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6974961757659912, "target_z": 0.2451171757551396, "ce": 5.927301406860352, "genuineness": 4.808597087860107, "identity": 0.7767890095710754, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/5e1fc0b2a67824247dbdc75b9fbb95820bd3f9088000495d7502bf2ef69a9f4b.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "5e2576b88c5108a7e18336cf08300f4c21fd1576fc791b4977261c2a42dbd740", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "977c4618ee53cbe23eb5c87219ee6ab56ca9a38bd52165ae2204f447e1ec0de1", "generation_seconds_batch": 23.551363318925723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4125303626060486, "target_z": -0.051269546082426794, "ce": 5.728734970092773, "genuineness": 4.645420074462891, "identity": 0.8441734313964844, "hypothesis": "La porte 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_Emotional_Numbness/5e2576b88c5108a7e18336cf08300f4c21fd1576fc791b4977261c2a42dbd740.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "5e335420e664421eb3e9ddb8ba524c4ea6a19a1e4750a8e9dfe9103783ff78b2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b8aad658319fa6de8378f7b15d7b9d1c0430dcb4385af460ece04b2322576b60", "generation_seconds_batch": 23.96922260604333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3219234347343445, "target_z": -0.1455078339313432, "ce": 6.0146708488464355, "genuineness": 4.6203155517578125, "identity": 0.7674825191497803, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5e335420e664421eb3e9ddb8ba524c4ea6a19a1e4750a8e9dfe9103783ff78b2.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": "5e37fa411316cab6e08875c851f8ca44db0b54c21a939cb9ddef2833685ab07a", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "244ef5adc9d344e2cce205458f2e2f1602c660a23fe777f4e348c754d6f44731", "generation_seconds_batch": 16.90348296496086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5120571255683899, "target_z": 0.05224606753595591, "ce": 5.542081832885742, "genuineness": 4.68307638168335, "identity": 0.7009280323982239, "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_Emotional_Numbness/5e37fa411316cab6e08875c851f8ca44db0b54c21a939cb9ddef2833685ab07a.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "5ea455f5299c79ae98cbdf0192e7b8f66f708c92afc30105116c02b59de4d88c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b46841395ebf77a1371ef8de5381bd30f2a23bb9a6921c80b29bcc636acbd02", "generation_seconds_batch": 25.299058718956076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5331830978393555, "target_z": 0.07421873014271026, "ce": 5.677107334136963, "genuineness": 4.419482707977295, "identity": 0.4435897171497345, "hypothesis": "De deur 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_Emotional_Numbness/5ea455f5299c79ae98cbdf0192e7b8f66f708c92afc30105116c02b59de4d88c.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "5eab66747a576b12ceed557b67b3eb64baa586ed51cff01b3e6c7412454cb3b0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "efbffd42d0eb1b2c7cf7c8cc1152957ff38a13918b01e7c0a54bbc6e7f44fcdf", "generation_seconds_batch": 25.617627715109847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11441951990127563, "target_z": -0.36132812621081034, "ce": 6.165581703186035, "genuineness": 4.7081804275512695, "identity": 0.7426271438598633, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/5eab66747a576b12ceed557b67b3eb64baa586ed51cff01b3e6c7412454cb3b0.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": "5ed3be39c5de0277e3d45aa2c7d6971f97c8fd06f723755b75e31985d9e4b995", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4a3d034c3981b21b750f19c68630a714996a507fcd1a94f213fe6a5153b77deb", "generation_seconds_batch": 26.777296588057652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.735992431640625, "target_z": 0.2851562911675519, "ce": 5.903473377227783, "genuineness": 4.570107460021973, "identity": 0.5648258924484253, "hypothesis": "De sleutels liggen op de keukentafel. Keken in de laag en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5ed3be39c5de0277e3d45aa2c7d6971f97c8fd06f723755b75e31985d9e4b995.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "5f06fa012759e65d35abebfb960e61fdc214b4fbe394d9b45b47ab8dd4675159", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "feae2ec3324cbd8db5873f86d0dfcb59eff195e9d46e1fffc9eb5376d7007bd0", "generation_seconds_batch": 21.175825201091357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5613510608673096, "target_z": 0.10351561361838271, "ce": 5.6532793045043945, "genuineness": 4.6705241203308105, "identity": 0.739920973777771, "hypothesis": "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_Emotional_Numbness/5f06fa012759e65d35abebfb960e61fdc214b4fbe394d9b45b47ab8dd4675159.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": "5fa7b3afe718468cb44ffedcf7d971f7913d8c62c363e6bac300851c4b0fa84a", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "af0b469824ca3a312c00c2f70b74183cd2ac5b8fe63318433bfa6ec8a0fbf33e", "generation_seconds_batch": 18.532203266979195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5529006719589233, "target_z": 0.09472654857568097, "ce": 5.903473377227783, "genuineness": 4.532451152801514, "identity": 0.6156936883926392, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5fa7b3afe718468cb44ffedcf7d971f7913d8c62c363e6bac300851c4b0fa84a.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "5faffb48ed0b66f33e4f8a09be4fb74a8e0426d7cebdfee8b8fcf2cdf02774d3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b8bb05bc7f96b60212987a161b338773a4967244fc6e13c7413efcfab7b85ca5", "generation_seconds_batch": 17.258823154959828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 6.165581703186035, "genuineness": 4.507347106933594, "identity": 0.4800208806991577, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5faffb48ed0b66f33e4f8a09be4fb74a8e0426d7cebdfee8b8fcf2cdf02774d3.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "5fca2fd78cd050eb0461d490678e7da3bfc7880b185a83803ba037621c919ff5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "47d3374bef68d6ad0e842cce10d845ea8e04771434b243d10c04f0c5c239a79a", "generation_seconds_batch": 24.34381599293556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5083014369010925, "target_z": 0.04833985773485955, "ce": 5.998785495758057, "genuineness": 4.494794845581055, "identity": 0.789210855960846, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5fca2fd78cd050eb0461d490678e7da3bfc7880b185a83803ba037621c919ff5.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "5ff636820bc2a8d9920ac634fdaaf69cadaf371e90ca4c28da7052b43a1eb7d2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "18bb7f9ec4a256eba4e16a41310b19a7cf8baf7eb85d765f5b46c945128860ac", "generation_seconds_batch": 18.980035469052382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16324397921562195, "target_z": -0.3105468718518931, "ce": 5.959072113037109, "genuineness": 4.582659721374512, "identity": 0.6168918609619141, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/5ff636820bc2a8d9920ac634fdaaf69cadaf371e90ca4c28da7052b43a1eb7d2.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": "60581cce321224dce7c9a6ee40dcd26747b7e88308d717ef31d9dc021c48b5cb", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab1a1c8c0350721d72b73b781cb9960feb9d2a46248220a3609716b575c113d7", "generation_seconds_batch": 25.67379918100778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25244247913360596, "target_z": -0.21777345917350527, "ce": 5.236289024353027, "genuineness": 4.758388519287109, "identity": 0.8460524082183838, "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_Emotional_Numbness/60581cce321224dce7c9a6ee40dcd26747b7e88308d717ef31d9dc021c48b5cb.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "607c873f026559bf122420f470516dc41fcc8f7365bccd55089725b6764cc04e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e55afca7e7dc4c393105ca7a1d89fac1bb7543dffebd593782121106c2dad2b7", "generation_seconds_batch": 25.227165518910624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27779364585876465, "target_z": -0.19140626404540007, "ce": 6.046441555023193, "genuineness": 4.7081804275512695, "identity": 0.8206527233123779, "hypothesis": "La porte 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_Emotional_Numbness/607c873f026559bf122420f470516dc41fcc8f7365bccd55089725b6764cc04e.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "60aca34d57a0269383678a737f7569c0aa8b1897ad806f81c361dfadebd19139", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2a940508ee3fa85b08d959abe1e53b72425b951ed57ddf1b58ca3455a5b939d3", "generation_seconds_batch": 26.432623769971542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0881294310092926, "target_z": -0.38867187378918966, "ce": 6.324435234069824, "genuineness": 4.6956281661987305, "identity": 0.4710482358932495, "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_Emotional_Numbness/60aca34d57a0269383678a737f7569c0aa8b1897ad806f81c361dfadebd19139.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "6106dd4a12a20f054929142fe9a40755c9414796bd5772a17b7d5c3a1a8ee64e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "65ee94b51ced6b2493e170218831d69a327dee3b1837df15a281f91a57fa64d6", "generation_seconds_batch": 24.302691091084853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2580760717391968, "target_z": -0.2119140824783708, "ce": 6.197352409362793, "genuineness": 4.595211505889893, "identity": 0.5991808176040649, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6106dd4a12a20f054929142fe9a40755c9414796bd5772a17b7d5c3a1a8ee64e.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "612fc6c0c07bcc6d6be3105a49fb65e1072ba1c50bc0930bc53d57aebe898fe7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "28c3c588d5be00c9946d7f3e988f4829e247317f83c011d10ccd42f7beab1a37", "generation_seconds_batch": 15.659033166011795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3721563220024109, "target_z": -0.09326170440189735, "ce": 5.728734970092773, "genuineness": 4.494794845581055, "identity": 0.716492235660553, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/612fc6c0c07bcc6d6be3105a49fb65e1072ba1c50bc0930bc53d57aebe898fe7.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "615f1a509264dd0e0166d2d1bf1bb07141222850794fc564aebb482f37db2775", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fdf8be21c38c02c13972e5612f673e7112a5bb3692bda234a062b94aa1b964d7", "generation_seconds_batch": 18.65611454891041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2796715199947357, "target_z": -0.18945312814810691, "ce": 6.046441555023193, "genuineness": 4.482243061065674, "identity": 0.6426689624786377, "hypothesis": "Ik 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_Emotional_Numbness/615f1a509264dd0e0166d2d1bf1bb07141222850794fc564aebb482f37db2775.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "617cc592a814ac545cff00226e99bf49796764b9a6a0b11b3725406b0fa34e1d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "325e84b7a3149a78813cedfbc9394314d30b7260cd69b2c28731cb14862e8045", "generation_seconds_batch": 23.004492571926676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09188514947891235, "target_z": -0.3847656329913483, "ce": 6.1894097328186035, "genuineness": 4.2751336097717285, "identity": 0.27494120597839355, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/617cc592a814ac545cff00226e99bf49796764b9a6a0b11b3725406b0fa34e1d.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": "61d6708985136aebbbaaf197afe661eeab2d5fb25ef78dc3aea954e12b7081e5", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "14861eff71b7b639256376616442cfe90cacdb58847e0702546e2ff2e65e0fe2", "generation_seconds_batch": 17.592817803029902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5735571980476379, "target_z": 0.11621095045567074, "ce": 5.879645347595215, "genuineness": 4.632867813110352, "identity": 0.6406859755516052, "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_Emotional_Numbness/61d6708985136aebbbaaf197afe661eeab2d5fb25ef78dc3aea954e12b7081e5.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "61ffc9b01647e37d907b92dcc61d57ff1a1f99a3cf2f482bceb02533b56a25bc", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "aa8914d88aa589644b1bbd3897fb8e20e05becea4d65ded8aeacb7b610433cea", "generation_seconds_batch": 22.774602573015727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2712211310863495, "target_z": -0.19824219319080866, "ce": 5.982900142669678, "genuineness": 4.758388519287109, "identity": 0.6580690741539001, "hypothesis": "La porte 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_Emotional_Numbness/61ffc9b01647e37d907b92dcc61d57ff1a1f99a3cf2f482bceb02533b56a25bc.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": "6210df4bc4780ed597902af0fa76a66fbfad5baa28f4378f04c5d364f9fa0012", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "0d90c9ff697d81475bd7a32d63bffbaab4712794b3f97badbe32c602b3e00727", "generation_seconds_batch": 19.441564140026458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5857632756233215, "target_z": 0.12890622529946885, "ce": 5.990842819213867, "genuineness": 4.607763767242432, "identity": 0.793125331401825, "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_Emotional_Numbness/6210df4bc4780ed597902af0fa76a66fbfad5baa28f4378f04c5d364f9fa0012.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "6228bc399925117f1cb59d660852281c5fb72dae2c9816dadcaf47879a1e506d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "afa0895b79138bc58488ce527f4aaaf960fe0c1abf9f5534c970a1d08e1c5135", "generation_seconds_batch": 25.914560534991324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35619446635246277, "target_z": -0.10986328203702672, "ce": 5.816103935241699, "genuineness": 4.632867813110352, "identity": 0.5296227335929871, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6228bc399925117f1cb59d660852281c5fb72dae2c9816dadcaf47879a1e506d.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "6230fa6070f7d2b61668f1e286434e8b7a588ff6bbe1bac31ee81f0ebf7d303c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "04805cad061f9aa3f9119ca8de0eecdd6be2b41366c55a1100fd0f33e2495ea2", "generation_seconds_batch": 21.926073455018923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17638900876045227, "target_z": -0.29687501356107593, "ce": 6.221180438995361, "genuineness": 4.808597087860107, "identity": 0.41376036405563354, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6230fa6070f7d2b61668f1e286434e8b7a588ff6bbe1bac31ee81f0ebf7d303c.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "6245a06144ec43c7222727a7152087b2ffae591c89a60e60f66867682711e128", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c52c0a3d3d1164bcaabff1f00df898077318393bbbbaf7604819db75ac2ddad1", "generation_seconds_batch": 18.540569615084678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36229753494262695, "target_z": -0.10351561361838271, "ce": 5.903473377227783, "genuineness": 4.507347106933594, "identity": 0.577705979347229, "hypothesis": "De deur 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_Emotional_Numbness/6245a06144ec43c7222727a7152087b2ffae591c89a60e60f66867682711e128.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "624ed9053aed0f90dfd04b68551ccfc069cd3eea91061729ca070bf35cfcc945", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1f737d31ea3a28482d04bbd68379b414a93a6f64ba17c72980586cd5bea0745b", "generation_seconds_batch": 26.276892377994955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5529006719589233, "target_z": 0.09472654857568097, "ce": 5.903473377227783, "genuineness": 4.331617832183838, "identity": 0.5208256840705872, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oudere 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_Emotional_Numbness/624ed9053aed0f90dfd04b68551ccfc069cd3eea91061729ca070bf35cfcc945.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "62cc969a07f96d7a9234537e33b372d7aeb6767d03a025dec53943cb05f4fe39", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a67c7bb2983c9cfee41f5778e1daf1fbf4b54698b1756cf00dc2c11e688e2672", "generation_seconds_batch": 24.499420738080516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 5.974957466125488, "genuineness": 4.469690799713135, "identity": 0.8191367387771606, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/62cc969a07f96d7a9234537e33b372d7aeb6767d03a025dec53943cb05f4fe39.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": "62f5ef93c34fb22b71ae2ab0e2c23145b8d0ded6fa2fd5662d8a53daa200d2b0", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "3655f4b60bb4ffe35306746f77e6521ac7de83682b4de31e4e1a95424f12bdcd", "generation_seconds_batch": 18.566232717013918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.602664053440094, "target_z": 0.1464843553848723, "ce": 5.681078910827637, "genuineness": 4.375550270080566, "identity": 0.48845183849334717, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder tot aan 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_Emotional_Numbness/62f5ef93c34fb22b71ae2ab0e2c23145b8d0ded6fa2fd5662d8a53daa200d2b0.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "63456c50ed30f7fa3fed7fc5088d3ebff1ae427f500fd0d63dd28b0368332508", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9aec2bc7ebc21319ce5d37caae697863eda69542a696ff15756ad76e6d22dca", "generation_seconds_batch": 21.83808705001138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5453892350196838, "target_z": 0.0869140669799983, "ce": 5.546053409576416, "genuineness": 4.758388519287109, "identity": 0.8133729100227356, "hypothesis": "La porte 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_Emotional_Numbness/63456c50ed30f7fa3fed7fc5088d3ebff1ae427f500fd0d63dd28b0368332508.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "635777e5049199081693da316ac82e8689cb9b68cadf1d6afd588db2cd01c62e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5667f36452bd22d9506f49b27caf111ca45b1a01bd12b61e5a5673682bf85037", "generation_seconds_batch": 18.827792212017812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.266526460647583, "target_z": -0.20312501743566905, "ce": 5.609594821929932, "genuineness": 4.7081804275512695, "identity": 0.7404646873474121, "hypothesis": "Fue 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_Emotional_Numbness/635777e5049199081693da316ac82e8689cb9b68cadf1d6afd588db2cd01c62e.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "637a9c2e75a4e96fa31a152a4d2199ea13662da6c44c35c3f6db46dc6ec009ca", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1f57bad0d852a86c2ce2f135656be27accc203baeb8834b1fa0f9030b8619f65", "generation_seconds_batch": 24.28177899005823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5439808368682861, "target_z": 0.08544922280621467, "ce": 5.8875885009765625, "genuineness": 4.570107460021973, "identity": 0.5950381755828857, "hypothesis": "De bor staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/637a9c2e75a4e96fa31a152a4d2199ea13662da6c44c35c3f6db46dc6ec009ca.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "6394988cb6b73ae0c97afa81c42c3ece0221fd812a0bb76c1c6aebb8883d12a6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e2ebc59e88e24c8e49e1837b0d4c8005b5d359dcb86aaa71b2d345fdfa37a124", "generation_seconds_batch": 23.916368031990714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3928128182888031, "target_z": -0.07177733351865254, "ce": 5.927301406860352, "genuineness": 4.632867813110352, "identity": 0.6673057675361633, "hypothesis": "Ik 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_Emotional_Numbness/6394988cb6b73ae0c97afa81c42c3ece0221fd812a0bb76c1c6aebb8883d12a6.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "63e4d5d3b290ad928cee2361c8700e65a945fe4f3b69b7be1496f3d0f53d1bf0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c4dc19dd6fa2a336ffb9e1893b24bdd4583378a0c6578eb57bb58ba37a4baa91", "generation_seconds_batch": 19.019297926919535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20831269025802612, "target_z": -0.26367188928756213, "ce": 6.252951145172119, "genuineness": 4.607763767242432, "identity": 0.6583669781684875, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/63e4d5d3b290ad928cee2361c8700e65a945fe4f3b69b7be1496f3d0f53d1bf0.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "6411d17fccd8e9faca18b737dac4b325b25f811296dd7f6a764cb67de95d6df3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c73c881dfab34bec506f56457eaaf379b56f9b836bad5f89119e86999f431ed", "generation_seconds_batch": 26.16970719897654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5857632756233215, "target_z": 0.12890622529946885, "ce": 5.903473377227783, "genuineness": 4.883909225463867, "identity": 0.8603859543800354, "hypothesis": "La porte 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_Emotional_Numbness/6411d17fccd8e9faca18b737dac4b325b25f811296dd7f6a764cb67de95d6df3.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "649311d60a4bc72198a646c98148ee9dbe36cd072cf67c2b6a48ae7d23bc3359", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6748b5c22d8ec1945d95af0b755bdced7f7c6bfa62f61b95902c97216f05a573", "generation_seconds_batch": 21.56451441394165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3782593607902527, "target_z": -0.0869140669799983, "ce": 6.292664527893066, "genuineness": 4.331617832183838, "identity": 0.6344171762466431, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/649311d60a4bc72198a646c98148ee9dbe36cd072cf67c2b6a48ae7d23bc3359.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "65b7975a4151009e08e99e0cafd3c20173fe3c4868e54f3fcf56ff885417ba13", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b89e30032013da732be58bd360d2fccad705a9b5be2b536c2a523a0d9e177d5d", "generation_seconds_batch": 18.428127496968955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42755329608917236, "target_z": -0.0356445208975715, "ce": 5.903473377227783, "genuineness": 4.444586753845215, "identity": 0.550898551940918, "hypothesis": "Ik 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_Emotional_Numbness/65b7975a4151009e08e99e0cafd3c20173fe3c4868e54f3fcf56ff885417ba13.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "65bc55dba598fb238ab46f0b68bcd72396efcf49eb0cf239f7267a74526acd30", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c22d940ef900042c4d4112d10ac3a8a5e323d6b21bc50add4dc94cfe5c1a001e", "generation_seconds_batch": 18.537311463966034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.640221357345581, "target_z": 0.18554688735026556, "ce": 5.19657564163208, "genuineness": 4.607763767242432, "identity": 0.744408369064331, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/65bc55dba598fb238ab46f0b68bcd72396efcf49eb0cf239f7267a74526acd30.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "65d6755a206d357c890f49cfb4385cb1852db70fe457d7afaa20ae67c7709dae", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "523f5e23f506a6a8be846a75013d122c665c26be3e3292feb8b587fc6ca351b1", "generation_seconds_batch": 19.45931131497491, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05057215690612793, "target_z": -0.42773437475783793, "ce": 6.356205940246582, "genuineness": 4.20609712600708, "identity": 0.3746086359024048, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/65d6755a206d357c890f49cfb4385cb1852db70fe457d7afaa20ae67c7709dae.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "66833ad9432f3e4870fca99558f1871ebfa9a861833e000c894a3132bc17e2e2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "310834cdd6d1eda573b00cf1c9b798abc3261489e6d80f6e741d0a03159824ec", "generation_seconds_batch": 25.24216042109765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11817523837089539, "target_z": -0.357421885412969, "ce": 6.300607204437256, "genuineness": 4.369274139404297, "identity": 0.3205905556678772, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/66833ad9432f3e4870fca99558f1871ebfa9a861833e000c894a3132bc17e2e2.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "67041655c4b51f86c4f9edc01e95a87778c3608241b758239bb10832ed23eea3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b171ecd2d5ef846e0b51a14450b30fc0ce0815a39762cec1cff642194a0d42e3", "generation_seconds_batch": 22.93450038204901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7791832685470581, "target_z": 0.3300781378345897, "ce": 5.681078910827637, "genuineness": 4.532451152801514, "identity": 0.7457922101020813, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/67041655c4b51f86c4f9edc01e95a87778c3608241b758239bb10832ed23eea3.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "6711654eff2d726b6799d890bb84181a498d5c790abbe1eef77adfb09a45614b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f5bebbc52f22816987bfc91260ca1c050968db4dda61922cd263b1b7cf6c8041", "generation_seconds_batch": 24.726480326033197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7040687203407288, "target_z": 0.2519531358972932, "ce": 5.808161735534668, "genuineness": 4.808597087860107, "identity": 0.7193517684936523, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/6711654eff2d726b6799d890bb84181a498d5c790abbe1eef77adfb09a45614b.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "6792d020fe4cd3cfd5078ab1f3e40bd9b24c55c80b4c50822cabcdae3d108b27", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "a25885e03b5af4343c595642819d3a1389f5df2aaa7ac45e24e813fc290897b2", "generation_seconds_batch": 24.091997882002033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40853992104530334, "target_z": -0.05541991724365041, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.6984701156616211, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6792d020fe4cd3cfd5078ab1f3e40bd9b24c55c80b4c50822cabcdae3d108b27.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "67ef0150136b1056fff4404b1c1c285645d64108422b82ecc5a9b914031a290a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "24e85ec17d346e1fd37a61130d0dd2c7fa298ddf9d5f6da693ff6ae0e94d2045", "generation_seconds_batch": 20.072934504947625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40267160534858704, "target_z": -0.06152342430216718, "ce": 6.125868320465088, "genuineness": 4.846253395080566, "identity": 0.7987719774246216, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/67ef0150136b1056fff4404b1c1c285645d64108422b82ecc5a9b914031a290a.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "684e6f7d3b5c8bae660ffbfeee5ba5f0fa8a2fb1a1a574a9ddc0eaf6cac5ea45", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "62eb5880ee3c8244a099597ef88852d6d8f6fe35c598c2f5d639849b495d9284", "generation_seconds_batch": 22.295547902002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2928165793418884, "target_z": -0.17578123886054478, "ce": 5.593709468841553, "genuineness": 4.570107460021973, "identity": 0.7978295087814331, "hypothesis": "La porte 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_Emotional_Numbness/684e6f7d3b5c8bae660ffbfeee5ba5f0fa8a2fb1a1a574a9ddc0eaf6cac5ea45.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "68e1bd795a444b0aaf8d05ee3b93892b3a6ac01e8a0a22adde2cd0696ceeb9c9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d34c61893c24bf4cfe017078ae940a749a8bb0ef921546f7933bbc066d566454", "generation_seconds_batch": 25.95442261500284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38295403122901917, "target_z": -0.0820312427351379, "ce": 5.824047088623047, "genuineness": 4.494794845581055, "identity": 0.6104052662849426, "hypothesis": "De deur 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_Emotional_Numbness/68e1bd795a444b0aaf8d05ee3b93892b3a6ac01e8a0a22adde2cd0696ceeb9c9.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": "695bc5c22411f114f418f8767a5b4286214a26b68352c7fa438695a7576817cb", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "675cd09be2efc5cb16efa5cc7cb177ae2446606580fee12d1f81ca396f5cabd7", "generation_seconds_batch": 19.75923647894524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4688662886619568, "target_z": 0.007324220868918113, "ce": 5.708878040313721, "genuineness": 4.65797233581543, "identity": 0.6878021955490112, "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_Emotional_Numbness/695bc5c22411f114f418f8767a5b4286214a26b68352c7fa438695a7576817cb.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "697e40c4fe87d7d4237b989b607264e145036fe2b42659e848e129a4348162a0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c02e87fce5b9493a90760b13f54a310a82e19c7813be5123b5f716c767c1c1f2", "generation_seconds_batch": 15.27863165398594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22709134221076965, "target_z": -0.24414062330486552, "ce": 5.919358730316162, "genuineness": 4.532451152801514, "identity": 0.631806492805481, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/697e40c4fe87d7d4237b989b607264e145036fe2b42659e848e129a4348162a0.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": "69b6b766c317fbba3b5d1ddd00eeee1a7060a3b36a4487841daabe8e6d7fad65", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Your message arrived after I had left.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "171c608b42660b2710e5e3f0215b09c6ee9a53edcc20e7180e29e61c3d376aa7", "generation_seconds_batch": 22.199890058021992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.751015305519104, "target_z": 0.3007812543589173, "ce": 5.959072113037109, "genuineness": 4.457139015197754, "identity": 0.33619439601898193, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know and we can talk.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/69b6b766c317fbba3b5d1ddd00eeee1a7060a3b36a4487841daabe8e6d7fad65.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": "69d7fd32d191d528fbea50384a6cccb7beea8003669c6be5f3e98dbc7d2fb52f", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ef1aa855fc74461b3c622de6a436a24ed972977f01686f63978d3aa993bdf6ab", "generation_seconds_batch": 17.10462384391576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7172137498855591, "target_z": 0.2656249941881103, "ce": 5.506340026855469, "genuineness": 4.6705241203308105, "identity": 0.8092098236083984, "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_Emotional_Numbness/69d7fd32d191d528fbea50384a6cccb7beea8003669c6be5f3e98dbc7d2fb52f.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "6a1c0fe2f9f01268a5531b4f78d3b3726a853a97a5fe110741302e02fcfe9c77", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "405a89da96462d250ad984ce7b0873437acd32457267292fea24a67c845fa0f4", "generation_seconds_batch": 22.14687237504404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8186184167861938, "target_z": 0.3710937747005311, "ce": 5.458683967590332, "genuineness": 4.796044826507568, "identity": 0.8473361134529114, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/6a1c0fe2f9f01268a5531b4f78d3b3726a853a97a5fe110741302e02fcfe9c77.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "6a4444bc6aa3cbbcee8e1d706dcbf3d1e5cd8b5cf120c2db1c20dd5bb219a74d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f00093039345a2a28dc41481e76831382ed054532802820703afabc0701f56fa", "generation_seconds_batch": 25.419141323072836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2975112199783325, "target_z": -0.17089844561242934, "ce": 6.046441555023193, "genuineness": 4.8588056564331055, "identity": 0.795881986618042, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6a4444bc6aa3cbbcee8e1d706dcbf3d1e5cd8b5cf120c2db1c20dd5bb219a74d.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": "6a4c58b64d23d7c42a6795ddf7f2dea7724158da05cb794f1f526fc17d8f9e44", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "c79253d8c89a0c8d4491bae6dd4e3e07e8ad6073a3d3e36b4ff1b630a1ac6566", "generation_seconds_batch": 18.22553607390728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5444502830505371, "target_z": 0.08593748353297924, "ce": 5.450741291046143, "genuineness": 4.607763767242432, "identity": 0.8193440437316895, "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_Emotional_Numbness/6a4c58b64d23d7c42a6795ddf7f2dea7724158da05cb794f1f526fc17d8f9e44.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "6a5e2289e2cc096286ffdc4d5393e9b92fd5d36e7044feea69b6746f6616a02a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "dcb28877cebcf0dbe32ce8d9d66d8959b4b51d25b764cdb361ef11591e8238c5", "generation_seconds_batch": 26.22193914593663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23929744958877563, "target_z": -0.23144531746432243, "ce": 5.935244083404541, "genuineness": 4.7081804275512695, "identity": 0.7483190298080444, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6a5e2289e2cc096286ffdc4d5393e9b92fd5d36e7044feea69b6746f6616a02a.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "03b42051e871c96980f307a36ef09e53d6892e9455198ef9e02cd31198b63051", "generation_seconds_batch": 17.968193753040396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06371721625328064, "target_z": -0.4140624854702758, "ce": 6.23706579208374, "genuineness": 4.080576419830322, "identity": 0.21052026748657227, "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_Emotional_Numbness/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "6b04d282296b037148247f31182587b0a2b1c061f62471deb02c0a677abf0c69", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f145559d9444acdca73342e3866d9057fc9b2cbcf03548acdca6e3fa129e8f4d", "generation_seconds_batch": 25.416390910046175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5857632756233215, "target_z": 0.12890622529946885, "ce": 6.022613525390625, "genuineness": 4.519899368286133, "identity": 0.6206691861152649, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6b04d282296b037148247f31182587b0a2b1c061f62471deb02c0a677abf0c69.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "6b2126044860ac94fed2b6e777ab15fb9d4b8d3874de9aacca3bf8558f751205", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "09d6da844a50283e6987918f7d8d16ae252b1e41553f4435398966a2a3dd2b14", "generation_seconds_batch": 25.95442261500284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 5.95112943649292, "genuineness": 4.519899368286133, "identity": 0.6037774682044983, "hypothesis": "De deur 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_Emotional_Numbness/6b2126044860ac94fed2b6e777ab15fb9d4b8d3874de9aacca3bf8558f751205.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "6b263067f96e19a98f9a8171f85b3260282544346f272c230facaa5f444877df", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "62a71cc2080d83c546cadc54d1ce0b2dccbc9719e920c4683af2ed6585a19519", "generation_seconds_batch": 24.739525887998752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46672433614730835, "target_z": 0.0050964228144474094, "ce": 5.450741291046143, "genuineness": 4.7081804275512695, "identity": 0.7747836709022522, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/6b263067f96e19a98f9a8171f85b3260282544346f272c230facaa5f444877df.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": "6b3c229fec1cc3406bf6b8a6294970509e735d486168238274b62615fa92f4a3", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1f55b8ebb8b60ac12dabc729058b7496ba765394eba3482d976e75aa893b0ef", "generation_seconds_batch": 26.777296588057652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0552291870117188, "target_z": 0.6171874719091999, "ce": 5.685050010681152, "genuineness": 4.482243061065674, "identity": 0.480894535779953, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het graam 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_Emotional_Numbness/6b3c229fec1cc3406bf6b8a6294970509e735d486168238274b62615fa92f4a3.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "6b6a805bfff7683d7524dadcca8cafe182747f90e14bd7d524333f7f26fd5424", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e5b16f0444e0316e48f7698ccfea00ee0732f1da2b659437fc003850cbd6bbe", "generation_seconds_batch": 25.50047402200289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3660532534122467, "target_z": -0.09960937282054137, "ce": 6.062326908111572, "genuineness": 4.720732688903809, "identity": 0.6277487874031067, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6b6a805bfff7683d7524dadcca8cafe182747f90e14bd7d524333f7f26fd5424.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "6b91af8e5ce949ce6c42c4cec15fb8076179bcc83174d8224163a6d65c632fc1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "abecb9b152fbe978a78f79ec65572f143982a7032168e859145b607a95e552ab", "generation_seconds_batch": 23.952000466990285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2533814311027527, "target_z": -0.2167968757264862, "ce": 5.974957466125488, "genuineness": 4.808597087860107, "identity": 0.703238308429718, "hypothesis": "La porte 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_Emotional_Numbness/6b91af8e5ce949ce6c42c4cec15fb8076179bcc83174d8224163a6d65c632fc1.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "83b780a06e4e2a3898c260dee9b12182a7a5af47c07cc49561572a5b35f31551", "generation_seconds_batch": 18.483289603027515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11441951990127563, "target_z": -0.36132812621081034, "ce": 6.221180438995361, "genuineness": 4.6705241203308105, "identity": 0.7285003066062927, "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_Emotional_Numbness/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.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": "6cc84299a52631cc459624121d99f25d40b5eb4c77cf5e8af7011ddc1da1219f", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a477e3da39b4c87a526557d66e5bd8aa66448b2202a8e7557b8b11302bf67cdc", "generation_seconds_batch": 23.77727673703339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5472670793533325, "target_z": 0.08886717188054648, "ce": 5.847874641418457, "genuineness": 4.7332844734191895, "identity": 0.8317989706993103, "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_Emotional_Numbness/6cc84299a52631cc459624121d99f25d40b5eb4c77cf5e8af7011ddc1da1219f.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "6cc9be81b7eea4767ebc687cd4627ef0343310e4424b3bfa3681b17a76e90c2d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "19a3c653c663a616798fcfc63d74b42db6793a08edd3cf01350a125735f9deb1", "generation_seconds_batch": 24.874736479949206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20831269025802612, "target_z": -0.26367188928756213, "ce": 6.149696350097656, "genuineness": 4.545003414154053, "identity": 0.6350926756858826, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6cc9be81b7eea4767ebc687cd4627ef0343310e4424b3bfa3681b17a76e90c2d.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "6d31c6e05d7b8de99eeb65fab1e194070b3809ec8ca175b83b9099eb2884952d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "259f3a83bee6c41642f1c6ee3980d97cdef7d391dd1cc5f4ceef8096e4a85733", "generation_seconds_batch": 18.980035469052382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28342723846435547, "target_z": -0.18554688735026556, "ce": 5.756534099578857, "genuineness": 4.400654315948486, "identity": 0.6969510316848755, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6d31c6e05d7b8de99eeb65fab1e194070b3809ec8ca175b83b9099eb2884952d.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "6e2489775d96e1354788fa824f2095d4f33a7488e9dbb73741095f76632d37b3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "35c70135621add178d68e791ad03cba6be72af3b884eec302c70d4be7755617c", "generation_seconds_batch": 26.468761850963347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5759044885635376, "target_z": 0.11865231608298349, "ce": 5.871703147888184, "genuineness": 4.381826400756836, "identity": 0.5077321529388428, "hypothesis": "Ik 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_Emotional_Numbness/6e2489775d96e1354788fa824f2095d4f33a7488e9dbb73741095f76632d37b3.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": "6e546e727aaac9e7c531265d6a42dd1712da6f6103bb3aa1b61aa125eb559a88", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4bec015ecc97d1e81b0c2f5df64800d8fbb501dc427e8290f4be69a3679944b1", "generation_seconds_batch": 27.407347153057344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7810611128807068, "target_z": 0.3320312427351379, "ce": 5.824047088623047, "genuineness": 4.7458367347717285, "identity": 0.722959041595459, "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_Emotional_Numbness/6e546e727aaac9e7c531265d6a42dd1712da6f6103bb3aa1b61aa125eb559a88.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "6e5e837b76fd77927fed65d8fc399e04d906a0d51958a1e7e60a9040c023780a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d0a5bf3bcb504ebc7133a8ff9cdce9357446cc817751a2e11d6f3ee7e42b5973", "generation_seconds_batch": 25.05612519197166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22145774960517883, "target_z": -0.25, "ce": 6.133810997009277, "genuineness": 4.883909225463867, "identity": 0.7464343309402466, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/6e5e837b76fd77927fed65d8fc399e04d906a0d51958a1e7e60a9040c023780a.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": "6e834d23fe51d6ab82e9d8c538068f68bb357d75996c4f7f50ff0eee337af494", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0ba893fe3decc36670dc2ea58a8996bd522e61678928be8465fdb3002848f01e", "generation_seconds_batch": 24.20789404900279, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8505420684814453, "target_z": 0.40429686797729997, "ce": 5.871703147888184, "genuineness": 4.632867813110352, "identity": 0.8203532695770264, "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_Emotional_Numbness/6e834d23fe51d6ab82e9d8c538068f68bb357d75996c4f7f50ff0eee337af494.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "6eb05e11752005e3b518339963c5beb99c5ff15565d9d58984308884329159b0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1b7d1885f2fee017beb7188965e4137ad8551b357a76f5d10711e16694fac36d", "generation_seconds_batch": 24.317944371025078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21206843852996826, "target_z": -0.25976561749297583, "ce": 6.117925643920898, "genuineness": 4.545003414154053, "identity": 0.38798144459724426, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6eb05e11752005e3b518339963c5beb99c5ff15565d9d58984308884329159b0.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "6ebe0e309956d96161e0bbc59c9887617da0271393cddbd10b9dfd4c834423c2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b443aa43dbaf1e706f96aa28c55570e3c8fdbdfdb4f3c2b898406e213b371607", "generation_seconds_batch": 21.926073455018923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18953406810760498, "target_z": -0.2832031242735138, "ce": 6.268836498260498, "genuineness": 4.7458367347717285, "identity": 0.3347935080528259, "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_Emotional_Numbness/6ebe0e309956d96161e0bbc59c9887617da0271393cddbd10b9dfd4c834423c2.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "6ee2ab9d80b41734a289ca2d04dadab3788c5a3e169ef43ce32f60b2c0850f18", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8527df1689cf7646df8f8cf3f698cc5fa324b0454828c85d6f919e3536924fbd", "generation_seconds_batch": 24.302691091084853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2308470606803894, "target_z": -0.24023438250702417, "ce": 6.133810997009277, "genuineness": 4.306513786315918, "identity": 0.6825482845306396, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/6ee2ab9d80b41734a289ca2d04dadab3788c5a3e169ef43ce32f60b2c0850f18.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "71d5c8dd6d286f20bd9871af09f4d7466b1c3e740ea7a9e25114e2c5d865b435", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "52d140cfe7be5b17c125d0e57943cbfc05513d352c16af82e5bf9cb34374910f", "generation_seconds_batch": 24.069222026038915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22896920144557953, "target_z": -0.24218750290594485, "ce": 5.8875885009765625, "genuineness": 4.218649387359619, "identity": 0.6828664541244507, "hypothesis": "La porte 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_Emotional_Numbness/71d5c8dd6d286f20bd9871af09f4d7466b1c3e740ea7a9e25114e2c5d865b435.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "7256f67cd49512872504f2f5775dc7eff614947f69e69f3be78c7a44b8ee7ac4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5302e1534637a7a28708bca1dd862531dd67fedec27d6e3dbb5248d687b72055", "generation_seconds_batch": 29.53206873999443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5421029925346375, "target_z": 0.0834961179056665, "ce": 5.391171455383301, "genuineness": 4.557555198669434, "identity": 0.6951074004173279, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7256f67cd49512872504f2f5775dc7eff614947f69e69f3be78c7a44b8ee7ac4.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "72bd08ad3c44756f824a34549b653be55c732b7bf46324930cda292648215f74", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "086fc3006f9e608090a9d0a4304f250e6421c7f09d581b17e7cbf163f5ec5bf0", "generation_seconds_batch": 24.207531283958815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4193376302719116, "target_z": -0.04418945557689096, "ce": 6.062326908111572, "genuineness": 4.369274139404297, "identity": 0.5972269177436829, "hypothesis": "Ik 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_Emotional_Numbness/72bd08ad3c44756f824a34549b653be55c732b7bf46324930cda292648215f74.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "732eec55a8632df960227c1b75ce1b181fdff82f0637b2379a66c59aef6b17ba", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b541fcddead0ad83f4b886d78faa1a49eb3b40a4c9834a8ca6386237a7c38780", "generation_seconds_batch": 18.74371704494115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6242594718933105, "target_z": 0.1689452787183912, "ce": 5.685050010681152, "genuineness": 4.632867813110352, "identity": 0.19258546829223633, "hypothesis": "De deur 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_Emotional_Numbness/732eec55a8632df960227c1b75ce1b181fdff82f0637b2379a66c59aef6b17ba.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "74074e0828752f83a714decc31be369675862434fb4b2ef3865693d8fa7f7d24", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7ed769460fb171ac5c4b1ec05b23ce9993a49b14c4d2f6f04031408c2405d355", "generation_seconds_batch": 24.021391859976575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33225172758102417, "target_z": -0.13476560199460333, "ce": 6.09409761428833, "genuineness": 4.7834930419921875, "identity": 0.8029923439025879, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/74074e0828752f83a714decc31be369675862434fb4b2ef3865693d8fa7f7d24.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "741ac23bea3d706f7fad61d208fa190bdc97b60bc48ff040eb96200ac3f10975", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15f2d4e707d14b6d38e2752e1c4e402c007943fd8c9501518d390f6e6dc9ddf4", "generation_seconds_batch": 26.286469950922765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2177020162343979, "target_z": -0.25390625629621383, "ce": 5.959072113037109, "genuineness": 4.231201171875, "identity": 0.2775745391845703, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/741ac23bea3d706f7fad61d208fa190bdc97b60bc48ff040eb96200ac3f10975.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "742c0335ba4315312f94f646d0251e06b00f46be07ef59a77c421a4c83f6f9d1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "aaaa6cfe6361058b1ceb254e4487d130403c6a64be6a34447f2a0016fcb34dbd", "generation_seconds_batch": 26.04954740498215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1388317346572876, "target_z": -0.3359375145297242, "ce": 6.165581703186035, "genuineness": 4.381826400756836, "identity": 0.709053099155426, "hypothesis": "La porte 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_Emotional_Numbness/742c0335ba4315312f94f646d0251e06b00f46be07ef59a77c421a4c83f6f9d1.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "74588940ce34919a5024cca4fc0db380da02089410330b312b780a5a0888979e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8cd38ed858ac54ec1789b04746b5a6d2ef2a6fa9ed5ae2e35d65f943b6b7af80", "generation_seconds_batch": 24.654590261052363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5223854184150696, "target_z": 0.06298829947269577, "ce": 5.982900142669678, "genuineness": 4.557555198669434, "identity": 0.35039496421813965, "hypothesis": "De deur 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_Emotional_Numbness/74588940ce34919a5024cca4fc0db380da02089410330b312b780a5a0888979e.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": "74877e3437469dcf78e15f43a2c4bac005eedd1fd9c753e86e9d571bd70476c3", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "71fd51d17d526fa5a74ce29dde6a1837ac48b6fe84385f2be14c57250e97e524", "generation_seconds_batch": 18.548494021059014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5167518258094788, "target_z": 0.057128922777561285, "ce": 5.732706069946289, "genuineness": 4.432034492492676, "identity": 0.48311352729797363, "hypothesis": "De sleutels liggen op de keukentafel. Kijk in de laar en daarna naast dat raam. Neem ze mee als je weggaat.", "wer": 0.18181818181818182, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/74877e3437469dcf78e15f43a2c4bac005eedd1fd9c753e86e9d571bd70476c3.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": "74c9cd648999d6e9f1b7bb07000e13a125f519524e877d4dbfc910c4bc132ac5", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "c1bf06f517135eb8535de8102ca6dfb3097be3297073ebcae77fce8b29a50707", "generation_seconds_batch": 18.462995297973976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7547709941864014, "target_z": 0.30468746416001363, "ce": 5.4666266441345215, "genuineness": 4.582659721374512, "identity": 0.6690241098403931, "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": 0.120000000000001, "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_Emotional_Numbness/74c9cd648999d6e9f1b7bb07000e13a125f519524e877d4dbfc910c4bc132ac5.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "7524b92a013ac677a130473940c5a687c3918bafacf9c5ebf20b3bc88691b6ac", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "02f7984a83d7074791b53dd6ae302ada044c50d9138903bec29f03cecc23f2fd", "generation_seconds_batch": 20.607228875043802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0402063131332397, "target_z": 0.6015625087178346, "ce": 5.34748649597168, "genuineness": 4.6203155517578125, "identity": 0.5299761295318604, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7524b92a013ac677a130473940c5a687c3918bafacf9c5ebf20b3bc88691b6ac.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "754cab27ce14e7536f3a1faa69b03c2a712daff67c6b6d296b639e20b59e3da1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "02f19c96fed418dc98eea309a20a7d9a136d3de7b12365d4eb9187f4010ec8dd", "generation_seconds_batch": 26.14811315399129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18953406810760498, "target_z": -0.2832031242735138, "ce": 6.348263263702393, "genuineness": 4.425758361816406, "identity": 0.24276761710643768, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/754cab27ce14e7536f3a1faa69b03c2a712daff67c6b6d296b639e20b59e3da1.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "754df453f2b91ef5535a2024504e23ea4a4affd78704e06e3ac1124dbf0f2883", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78b0c622c52769a0cba36acb998afbc3ae44794508e5c0a8c81da67a9c2c2bbf", "generation_seconds_batch": 24.730744856991805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44363248348236084, "target_z": -0.018920909077495954, "ce": 5.6254801750183105, "genuineness": 4.507347106933594, "identity": 0.45037415623664856, "hypothesis": "De deur 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_Emotional_Numbness/754df453f2b91ef5535a2024504e23ea4a4affd78704e06e3ac1124dbf0f2883.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "7551e1897cd14c0edde3f0060f3445da8be2f84d87daa03debbe38cc1796d0b3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "181deb66b8db41bb3891586e3397d3b25387b1a2ecc0ba766c670baa75152381", "generation_seconds_batch": 23.00942736095749, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.876832127571106, "target_z": 0.4316405845589343, "ce": 5.2640886306762695, "genuineness": 4.7081804275512695, "identity": 0.6596773862838745, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7551e1897cd14c0edde3f0060f3445da8be2f84d87daa03debbe38cc1796d0b3.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "75a3120845636855e02be26c89ec88f75c8ea24b2c232acd7c3c9a5d926bee5a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7951e8b21da6fa3fe3d09550c59958afa49d8953c84b5e00fbf141320a009fb4", "generation_seconds_batch": 21.357351392973214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6195648312568665, "target_z": 0.1640624854702758, "ce": 5.4666266441345215, "genuineness": 4.758388519287109, "identity": 0.7481053471565247, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/75a3120845636855e02be26c89ec88f75c8ea24b2c232acd7c3c9a5d926bee5a.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "75d9f2d480dcddea4ea29a80ee8cc1b9a8f623cb216bf2fbd98b7ef92163683d", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "97286ea93626cab7b952da6680df7cbbde412b3e2a59f5475f290f44390e5052", "generation_seconds_batch": 18.92763454897795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1388317346572876, "target_z": -0.3359375145297242, "ce": 6.332377910614014, "genuineness": 4.582659721374512, "identity": 0.549521803855896, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/75d9f2d480dcddea4ea29a80ee8cc1b9a8f623cb216bf2fbd98b7ef92163683d.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "76b3f238aed0027ca8f5e912ace579ec4b018f614b8b8ac13b15dce15f70e26d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f96d6d30d15a3bf8289b5cc12be9132c49d234d3b6a6c94dae5c6b76ae07814d", "generation_seconds_batch": 22.867939891992137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2177020162343979, "target_z": -0.25390625629621383, "ce": 6.316492557525635, "genuineness": 4.545003414154053, "identity": 0.3513537049293518, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/76b3f238aed0027ca8f5e912ace579ec4b018f614b8b8ac13b15dce15f70e26d.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "7709f3c001d1824b897a066fd7fea85911395b7314492f11e51f323df97c014a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "707c4dba463c19b7d95d7f35fb405e4de5452f491b8d3004052b32c0b596f6db", "generation_seconds_batch": 24.377507732016966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5125266313552856, "target_z": 0.05273439025621041, "ce": 5.839932441711426, "genuineness": 4.7834930419921875, "identity": 0.68644118309021, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7709f3c001d1824b897a066fd7fea85911395b7314492f11e51f323df97c014a.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "770f83ebe20513230048fe9cd130eee25d1fe995ba19cc249ca89e6b4bd00c58", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "33de15aa63fa84a73a03b28553dfa3b5123d4dab82d348df4110f429de6e7efb", "generation_seconds_batch": 16.79622072901111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06935077905654907, "target_z": -0.40820313977188627, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.6261216402053833, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/770f83ebe20513230048fe9cd130eee25d1fe995ba19cc249ca89e6b4bd00c58.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "9eb9de9eb3fc46696cae1da7f04844492fddb2bda5810d029781a21fa1764d1b", "generation_seconds_batch": 18.792211055057123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23741959035396576, "target_z": -0.2333984378632431, "ce": 6.205295085906982, "genuineness": 4.570107460021973, "identity": 0.7213131189346313, "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_Emotional_Numbness/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "77cf6ac1a115200cd8686d1fe93abc86d18939f6a2de162dd0d1e4bc3aff0401", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "29ffc38f1741ed9fcf250f45c379c91ccfbf2684ea21bb9be90543497405adbb", "generation_seconds_batch": 25.80477549904026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3439883589744568, "target_z": -0.1225585878775698, "ce": 5.808161735534668, "genuineness": 4.507347106933594, "identity": 0.6602474451065063, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/77cf6ac1a115200cd8686d1fe93abc86d18939f6a2de162dd0d1e4bc3aff0401.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "7831dbef1ba7cde8ba7a1ed2acbacc637d9cdea54962d87cdd57492139c3fe0d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ae64cfb81087a0c56f90ebe21669addde84b82672ac26d985d701411eee9c31d", "generation_seconds_batch": 24.184396581957117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21957989037036896, "target_z": -0.25195312039892065, "ce": 6.006728172302246, "genuineness": 4.720732688903809, "identity": 0.7648719549179077, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7831dbef1ba7cde8ba7a1ed2acbacc637d9cdea54962d87cdd57492139c3fe0d.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "7916928bb8c9ef56611ee86c2591f464b7798066f588c2a408c3cf85675443e0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "93218c5e846320951b5417d99285ab40bf8baebc63f8f02624ca8ca3b2979bed", "generation_seconds_batch": 18.387534435023554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22709134221076965, "target_z": -0.24414062330486552, "ce": 6.157639026641846, "genuineness": 4.369274139404297, "identity": 0.7267167568206787, "hypothesis": "Ik 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_Emotional_Numbness/7916928bb8c9ef56611ee86c2591f464b7798066f588c2a408c3cf85675443e0.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "7943356f945579d59cca200084d19a3220834e6b3a6ebd5dd78f5cd21fdde704", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "fdbbc332718a056827a7da373699c7e621a9f29fdbbe973497d07c564af687ec", "generation_seconds_batch": 25.216349124908447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41863343119621277, "target_z": -0.04492187766378277, "ce": 5.974957466125488, "genuineness": 4.7458367347717285, "identity": 0.5835649967193604, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7943356f945579d59cca200084d19a3220834e6b3a6ebd5dd78f5cd21fdde704.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "5df60242bd03e7ac5239fd77d0817cb9e8435252307ffe171214b57b9ffe4de7", "generation_seconds_batch": 17.59475459193345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09939661622047424, "target_z": -0.37695312039892065, "ce": 6.046441555023193, "genuineness": 4.293961524963379, "identity": 0.488347589969635, "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_Emotional_Numbness/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "7983ba6bc53ceb3539beeff40f6b76dfc633730f9f310c30f8de21dd2bd31655", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a4f1795cf42375dd844bdd9da34651b77eb56206cd4389d311db50f2887a4bd5", "generation_seconds_batch": 18.002406697021797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3482135534286499, "target_z": -0.11816405535621893, "ce": 6.054384231567383, "genuineness": 4.425758361816406, "identity": 0.7390298843383789, "hypothesis": "De deur 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_Emotional_Numbness/7983ba6bc53ceb3539beeff40f6b76dfc633730f9f310c30f8de21dd2bd31655.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "79bbf28ef209670240f578094976643d7afed5e99cabfcb45b75e92ab5aef08f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "53f80be2d765db2d680045820e64c5cc81ae61ce8d8d0dc5dc055b8f3ae15f6c", "generation_seconds_batch": 27.29841075197328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19892337918281555, "target_z": -0.27343750678053796, "ce": 6.308549880981445, "genuineness": 4.7834930419921875, "identity": 0.7580417990684509, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/79bbf28ef209670240f578094976643d7afed5e99cabfcb45b75e92ab5aef08f.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "7a19d2e57efcaacc5fbe8520bbcb13e0ade6c7feb42b7e9ae01f544f925d0787", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "61d118ea792056d75c0b8b1b94c885be87142dd6d57d5faaa4690a7821558d32", "generation_seconds_batch": 22.97360586898867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2233356088399887, "target_z": -0.24804687960107932, "ce": 6.197352409362793, "genuineness": 4.632867813110352, "identity": 0.27821290493011475, "hypothesis": "The 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_Emotional_Numbness/7a19d2e57efcaacc5fbe8520bbcb13e0ade6c7feb42b7e9ae01f544f925d0787.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "7a1ee4018a62a780dae45236c13c3b7dfbf30e401f5cfec50cb00cf4c63835f1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "8a0ab758d53ff72ee35f516adb46f8f39e97abfb7489d9f3a3fda748e066aa60", "generation_seconds_batch": 23.44354350399226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5003204941749573, "target_z": 0.040039053418922374, "ce": 5.847874641418457, "genuineness": 4.7332844734191895, "identity": 0.6375481486320496, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7a1ee4018a62a780dae45236c13c3b7dfbf30e401f5cfec50cb00cf4c63835f1.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "7a84cf1efd7ea85e70f8d4fb312230dad227c81e07b36dfa53952fb56f8bf8f8", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "217cca6ed5e6a90773a5bca734f59289ada1d7d557210d250ef99c27bf962d9b", "generation_seconds_batch": 18.999958459986374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27216005325317383, "target_z": -0.19726564074053454, "ce": 6.133810997009277, "genuineness": 4.7332844734191895, "identity": 0.5508925914764404, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7a84cf1efd7ea85e70f8d4fb312230dad227c81e07b36dfa53952fb56f8bf8f8.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "7aa541dde9edbc6e201a41bf5ddb1809ba3e10fef74ca4ec2eedcaf5e0ec2bae", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0e180f6944c72b9e2b5edb953e681748969b027b771dfbfa06f7644a6798780f", "generation_seconds_batch": 26.03815897309687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1876561939716339, "target_z": -0.2851562601708069, "ce": 6.0305562019348145, "genuineness": 4.557555198669434, "identity": 0.5703587532043457, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7aa541dde9edbc6e201a41bf5ddb1809ba3e10fef74ca4ec2eedcaf5e0ec2bae.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "7ab0c54b4dd499409abb743fa52002fe328d268788958208dffa4a9e0c1b956f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e3756065ad156600a2452e14e171991d72f0511fd2dfc4018c87d339fe6a7325", "generation_seconds_batch": 26.413259892025962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07874011993408203, "target_z": -0.3984374912821655, "ce": 6.340320587158203, "genuineness": 4.582659721374512, "identity": 0.5575418472290039, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7ab0c54b4dd499409abb743fa52002fe328d268788958208dffa4a9e0c1b956f.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "7ab60ecc2cfd2fef079843aebff3f8c2ebfc8729abec4bebafb6c1c1febcc425", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2ce76054efec2eef942d3ad4fb1635d20320e8ea3c103d26f2de252c2d9c5a9a", "generation_seconds_batch": 18.319008890073746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11066380143165588, "target_z": -0.3652343670086517, "ce": 6.070269584655762, "genuineness": 4.632867813110352, "identity": 0.8371762633323669, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/7ab60ecc2cfd2fef079843aebff3f8c2ebfc8729abec4bebafb6c1c1febcc425.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "7ab6c4620d2ad122a668fbad5d9f2c4ae402899d9d1e1b99dba486f6ea238533", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5c3a2d6b8a718f04d02baf67c9ff21e5079b5b37c06cd6c204af429e35a8eb57", "generation_seconds_batch": 26.04954740498215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.103152334690094, "target_z": -0.37304687960107935, "ce": 6.141753673553467, "genuineness": 4.545003414154053, "identity": 0.7079459428787231, "hypothesis": "La porte 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_Emotional_Numbness/7ab6c4620d2ad122a668fbad5d9f2c4ae402899d9d1e1b99dba486f6ea238533.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "7bfcc09dd9df3f59b487c138c3da40c3c0d313541063ce79a4cd773cef6a2c7d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "12543af66446ad35656dfea24a4f23186d7d72d82c368e1c62907d0e078132cd", "generation_seconds_batch": 22.711115163983777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6683893203735352, "target_z": 0.21484377082593803, "ce": 6.062326908111572, "genuineness": 4.507347106933594, "identity": 0.6258032321929932, "hypothesis": "La puerta siguió abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7bfcc09dd9df3f59b487c138c3da40c3c0d313541063ce79a4cd773cef6a2c7d.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "7c905a9b5b4c435ff837cd08f579599d0545352342c5a3a98795fb7b743e05fd", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2ef715df00fca3fa0c0bfebbb72afce6e15af6fc73a92ab6f97cad2c34efb4ed", "generation_seconds_batch": 18.577911864966154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.540225088596344, "target_z": 0.08154295101162837, "ce": 5.871703147888184, "genuineness": 4.770940780639648, "identity": 0.8042877912521362, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/7c905a9b5b4c435ff837cd08f579599d0545352342c5a3a98795fb7b743e05fd.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "7cd0992672333cb83eac47a71aea78bd3ff445a61d5c3de2b6e7fb3ced0b7a52", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8ae61c3bf269811bc1840dcf89b2ac95cd9b320d4c26a7ffc6f32f9b320c5082", "generation_seconds_batch": 23.116709231981076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1313202977180481, "target_z": -0.34374999612540685, "ce": 6.403861999511719, "genuineness": 4.532451152801514, "identity": 0.4946253299713135, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7cd0992672333cb83eac47a71aea78bd3ff445a61d5c3de2b6e7fb3ced0b7a52.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "7d54e79454806c60f11237740ff092a0184c22b09c99f3b41e1bac507e4d2400", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a04997c7187ecde441135d29e7c80730f1ba8441883b762192c41983d4c034eb", "generation_seconds_batch": 25.34207286394667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9031222462654114, "target_z": 0.45898436313405855, "ce": 5.2045183181762695, "genuineness": 4.720732688903809, "identity": 0.7150229215621948, "hypothesis": "La puerta sigue abierta. me he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7d54e79454806c60f11237740ff092a0184c22b09c99f3b41e1bac507e4d2400.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "7d78ac672e24e8575d8a5199ec587511fe24f009eb78c98f9b884d04ea7c370b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8dbf1dc38ea0faaae9543e3384c33842e76a8e5a51065575b0330e6a6b9fa6b1", "generation_seconds_batch": 16.05060944892466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16136610507965088, "target_z": -0.31250000774918624, "ce": 6.133810997009277, "genuineness": 4.344170093536377, "identity": 0.6208485960960388, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7d78ac672e24e8575d8a5199ec587511fe24f009eb78c98f9b884d04ea7c370b.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "7d8d7f8ce3026ee81990f7e7703b0577edd5cfdcc6d1528dea500229b7cd7e20", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2dd1181b45aac496b7862e46272c080e5a30892b6b5d43c624f45f5dec8b9089", "generation_seconds_batch": 26.243028732948005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16136610507965088, "target_z": -0.31250000774918624, "ce": 6.252951145172119, "genuineness": 4.607763767242432, "identity": 0.7098582983016968, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7d8d7f8ce3026ee81990f7e7703b0577edd5cfdcc6d1528dea500229b7cd7e20.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "7e3fb249421b94cb808c1682d6dd599ee5caea8af59e14063f0d93622deb9514", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a2ea56b1015292490006f9aa32af4fdfede0dd2f72b54f8f53281b0d026868dd", "generation_seconds_batch": 26.432623769971542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11254164576530457, "target_z": -0.3632812621081035, "ce": 6.324435234069824, "genuineness": 4.632867813110352, "identity": 0.32440245151519775, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7e3fb249421b94cb808c1682d6dd599ee5caea8af59e14063f0d93622deb9514.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "7ed29a03271caa414ac62aeb905cc145a4d4ced0c7f7012eb7c25b79251ff644", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "740622f5857e3148d3556ee7cf1bfb9020b7be8991a62de1b7fe9f4bc92ef179", "generation_seconds_batch": 23.69255176198203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7960840463638306, "target_z": 0.3476562679199932, "ce": 5.95112943649292, "genuineness": 4.432034492492676, "identity": 0.5715045928955078, "hypothesis": "Ik 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_Emotional_Numbness/7ed29a03271caa414ac62aeb905cc145a4d4ced0c7f7012eb7c25b79251ff644.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "7ef5a63ef8e89ff31285b1e284854aab8e7f2607b1b312aaa0f6a93e8e69b576", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f4461a4feab22f7c9862fbb50b90a109f32bbfa887d3e422ec54625329836779", "generation_seconds_batch": 23.14350464392919, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3468051552772522, "target_z": -0.11962889953000255, "ce": 5.395142555236816, "genuineness": 4.419482707977295, "identity": 0.420480340719223, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/7ef5a63ef8e89ff31285b1e284854aab8e7f2607b1b312aaa0f6a93e8e69b576.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": "7f512d736f7445f7ce581fbcc4976c18ba04ce255035e1657a2109a863647455", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The road turns left behind the bridge.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "79daf1137c97ff5bef787de7d7ec93dac1b8278b09bc080fc00c18daa591b339", "generation_seconds_batch": 27.485473950044252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5486754775047302, "target_z": 0.0903320160543301, "ce": 6.062326908111572, "genuineness": 4.545003414154053, "identity": 0.344688355922699, "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_Emotional_Numbness/7f512d736f7445f7ce581fbcc4976c18ba04ce255035e1657a2109a863647455.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "7f6b94387b9dcfceecac09cc46f7f7591eda665acba5163c755f03040a3cf943", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bc709c050f8fe32fdd49d949adb94498257cff1ab074d64f8a93b64c23954593", "generation_seconds_batch": 17.940340842003934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5904579758644104, "target_z": 0.13378908054107422, "ce": 5.728734970092773, "genuineness": 4.6705241203308105, "identity": 0.7011643648147583, "hypothesis": "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_Emotional_Numbness/7f6b94387b9dcfceecac09cc46f7f7591eda665acba5163c755f03040a3cf943.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "ddafb76ca483b81c8c39566f2fbd65b006a15a51b69316b75ac960517b37f153", "generation_seconds_batch": 17.94133065699134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05808362364768982, "target_z": -0.4199218621654103, "ce": 6.38797664642334, "genuineness": 4.18099308013916, "identity": 0.4241136312484741, "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_Emotional_Numbness/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "7fa3b8bef0194511139e90702f1e391f7ec8177a17a065b2436cf570fa0b3ddb", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a4f1048dc471867ef8fefca05fe80d727e2740b9674b49b962deaf231499519a", "generation_seconds_batch": 21.652356379083358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3942212164402008, "target_z": -0.07031248934486892, "ce": 5.824047088623047, "genuineness": 4.457139015197754, "identity": 0.5929383635520935, "hypothesis": "De deur 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_Emotional_Numbness/7fa3b8bef0194511139e90702f1e391f7ec8177a17a065b2436cf570fa0b3ddb.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "7fd4a56f62b4e31e01c806fef866855b1150a59bca0af705ee219ede2183d9c1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f11a1a79e85919ea7fd1838ced1a23318ba1a7b1606f12d599509b78aed5daca", "generation_seconds_batch": 24.448036584071815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4296658933162689, "target_z": -0.03344725463689607, "ce": 5.4825119972229, "genuineness": 4.607763767242432, "identity": 0.7810837626457214, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/7fd4a56f62b4e31e01c806fef866855b1150a59bca0af705ee219ede2183d9c1.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "8072db55c0ddb79e826f8f6a0a5227276f8cb978d8caaf9bcb3c1b05516e8698", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af25c37d9546414df3f399c0734d7bcf1fbcee70781bfd91710975053ffe8d7c", "generation_seconds_batch": 21.677612161962315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5209770202636719, "target_z": 0.06152345529891215, "ce": 5.748591423034668, "genuineness": 4.381826400756836, "identity": 0.7540059089660645, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8072db55c0ddb79e826f8f6a0a5227276f8cb978d8caaf9bcb3c1b05516e8698.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "abe1aa42fd88f62b5bae520d70ca2ad21eb8d4cd6e531579bb484043772e2104", "generation_seconds_batch": 19.947708321968094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12944242358207703, "target_z": -0.34570313202270003, "ce": 6.24500846862793, "genuineness": 4.331617832183838, "identity": 0.695242166519165, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "80fdfedcb5336612b8fadbce37bdd92b1c9954586aaa21e1ab98b88c6197ba3d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fde86331a0a9006242469bc28ba0fab06068e1850ab7114d5d4a6a7a514d3432", "generation_seconds_batch": 18.707334491075017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2618318200111389, "target_z": -0.20800781068378446, "ce": 6.340320587158203, "genuineness": 4.532451152801514, "identity": 0.40221017599105835, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/80fdfedcb5336612b8fadbce37bdd92b1c9954586aaa21e1ab98b88c6197ba3d.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "815fc31583efe58be27c9d07e5946570160be36f0938418153435985f9d09aba", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fc166b16f5a0db968548e216e1afe5938c6f566219e0b424a3fe2a85d55eb654", "generation_seconds_batch": 19.540201906929724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5195686221122742, "target_z": 0.06005861112512853, "ce": 5.967014789581299, "genuineness": 4.507347106933594, "identity": 0.5049105882644653, "hypothesis": "De deur 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_Emotional_Numbness/815fc31583efe58be27c9d07e5946570160be36f0938418153435985f9d09aba.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "8177d11b67fd36535c2e6bdc3bfb2cf7b3d078919e2a86fd5430ebf5df7deef8", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3d58a6ec6d9337f7f5dfb173f91fdbbf69b518aa03f2ae827391f4cfe021ccf2", "generation_seconds_batch": 25.393609042977914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30126696825027466, "target_z": -0.16699217381784304, "ce": 6.316492557525635, "genuineness": 4.68307638168335, "identity": 0.38566774129867554, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8177d11b67fd36535c2e6bdc3bfb2cf7b3d078919e2a86fd5430ebf5df7deef8.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": "81893670ce0737e7819ae0ab42ca02c1d663089d0467146500fbda82fbc24353", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f297129a455fa1ef933d77087edede6d44f658145d33d8c58da2bbcc20ba67d", "generation_seconds_batch": 27.407347153057344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7679160833358765, "target_z": 0.3183593844443207, "ce": 5.847874641418457, "genuineness": 4.758388519287109, "identity": 0.7393953800201416, "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_Emotional_Numbness/81893670ce0737e7819ae0ab42ca02c1d663089d0467146500fbda82fbc24353.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "81a1704a048b5585398dd0f133b894def51a8a80312951c9b7774c755da520be", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "164d2d6ee3c4d0f1e749bff2de60df02625fdd2c65ff62d8865652a0b46199a6", "generation_seconds_batch": 24.520811351016164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.215824156999588, "target_z": -0.2558593766951345, "ce": 5.903473377227783, "genuineness": 4.68307638168335, "identity": 0.7197743654251099, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/81a1704a048b5585398dd0f133b894def51a8a80312951c9b7774c755da520be.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": "824b50991b22837c7f086ef40c44d9676b325d89a9313204bb69a80139b836e2", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I wrote the number on the envelope.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0a30e6bfbde5582563c252b02641adb9ce8d8a2ebd744b28dda1729d2a0f9c0f", "generation_seconds_batch": 21.882813064032234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47989875078201294, "target_z": 0.018798843895804815, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.3664003312587738, "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_Emotional_Numbness/824b50991b22837c7f086ef40c44d9676b325d89a9313204bb69a80139b836e2.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "8345f959e033fe91cc8fa9da67e413dca01479161ce0a72ce001e20f3f6707f5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3c7f4d39e39cf1f2ed47e2806633ed1cf9f47c06c42ad59f35539ed3211bdaea", "generation_seconds_batch": 19.473334238980897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3735647201538086, "target_z": -0.09179686022811373, "ce": 5.998785495758057, "genuineness": 4.7332844734191895, "identity": 0.7801943421363831, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/8345f959e033fe91cc8fa9da67e413dca01479161ce0a72ce001e20f3f6707f5.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "83a15768bf9e86da55a955b3f4c61c51c042d6de2cd4c452cd31a4003bc08cb3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c7b9bc67c31f757d93f7c797fe5948c5a82c38946e7502fdde910dedb7f8e148", "generation_seconds_batch": 23.203048930037767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1594882607460022, "target_z": -0.3144531126497344, "ce": 5.8875885009765625, "genuineness": 4.356721878051758, "identity": 0.601150393486023, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/83a15768bf9e86da55a955b3f4c61c51c042d6de2cd4c452cd31a4003bc08cb3.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "861397fa0cdf7817c9c9d8c1ec9f3d57154123f57bf16bf5e6f7f5bf796568a9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7bee06a8beb574bfb0370fad21d862a072d201930b9176bc576d75f923964b5d", "generation_seconds_batch": 23.14350464392919, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18577834963798523, "target_z": -0.28710936507135515, "ce": 6.062326908111572, "genuineness": 4.6956281661987305, "identity": 0.2640222907066345, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/861397fa0cdf7817c9c9d8c1ec9f3d57154123f57bf16bf5e6f7f5bf796568a9.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "867d150484093fe073ad97ab3791b42dc12adec353faa0400c9e920ca6db6a64", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f11280e548b6dbd4fe3e0aaad08ef7000773f88e8d7a6769d4f00d41b7c06cb3", "generation_seconds_batch": 25.090135145001113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5298968553543091, "target_z": 0.07080078106837845, "ce": 5.367343425750732, "genuineness": 4.6705241203308105, "identity": 0.7782041430473328, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/867d150484093fe073ad97ab3791b42dc12adec353faa0400c9e920ca6db6a64.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "871ff1034bdd8a41873c188f4cdf5649a764bb33829adfa762c5c187699934d6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "98defa4f54048c7d6e85d19bdd719ad494880bc85f632a8293934c05e5fd7e16", "generation_seconds_batch": 15.423867790959775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4652279317378998, "target_z": 0.0035400452527679163, "ce": 6.1020402908325195, "genuineness": 4.570107460021973, "identity": 0.6826087236404419, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/871ff1034bdd8a41873c188f4cdf5649a764bb33829adfa762c5c187699934d6.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "87c21b42718d58f7d044d838898a49ad19aa7ac1e871410599729c45c1cb5cce", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ca584e094b91bcf273e0f863bc8547cd6e6013f47eca36648d1371c0e22cc9a6", "generation_seconds_batch": 26.05157958494965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2843661904335022, "target_z": -0.18457030390324652, "ce": 6.149696350097656, "genuineness": 4.375550270080566, "identity": 0.7115055322647095, "hypothesis": "Ik 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_Emotional_Numbness/87c21b42718d58f7d044d838898a49ad19aa7ac1e871410599729c45c1cb5cce.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "8874ff937b317bea467d5505f201940315d6a391e97289622359a82017cc2b1a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71e1749c58907a6e4edc09fe315f8b3c07de3c8464371f5673b4c4f59eeb1d61", "generation_seconds_batch": 20.289659190922976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7153359055519104, "target_z": 0.26367188928756213, "ce": 5.808161735534668, "genuineness": 4.356721878051758, "identity": 0.5237279534339905, "hypothesis": "De deur 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_Emotional_Numbness/8874ff937b317bea467d5505f201940315d6a391e97289622359a82017cc2b1a.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "88f235ad6c13caa2c297e91c3de6edc1fbd5c5011043a6a8f3a3bcc06c9389b0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4d2c58ec4b1973a79f0a170ee36d9f627a4a49916f4d19b55445b9ce179cb0b7", "generation_seconds_batch": 23.3287451940123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48271551728248596, "target_z": 0.021728501246627088, "ce": 5.895530700683594, "genuineness": 4.7458367347717285, "identity": 0.3665425181388855, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/88f235ad6c13caa2c297e91c3de6edc1fbd5c5011043a6a8f3a3bcc06c9389b0.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "896b4f459048d8fde8243de9c738b749991e28c8e3841d541610e7fc066f2b91", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cdba688266bea747792970af34b444683f112933110414387ae49d98b5699f26", "generation_seconds_batch": 23.924712667940184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2580760717391968, "target_z": -0.2119140824783708, "ce": 6.38003396987915, "genuineness": 4.457139015197754, "identity": 0.6605132818222046, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/896b4f459048d8fde8243de9c738b749991e28c8e3841d541610e7fc066f2b91.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "8a5742d5fcfed4cf635d3e847d2de12aefb6b0b10b0180338a0ed2c011d5e708", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be7eb56ff75addf1a86387ea02554d25baeb8bafe80bc1e56ecab6c32264e1b3", "generation_seconds_batch": 26.81849247601349, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11066380143165588, "target_z": -0.3652343670086517, "ce": 6.316492557525635, "genuineness": 4.607763767242432, "identity": 0.4897097945213318, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8a5742d5fcfed4cf635d3e847d2de12aefb6b0b10b0180338a0ed2c011d5e708.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "8a59f753700aff9f6262dff4a179b7a185db37a7c46c7b4e401444d84066f984", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7d18acc602189c364fc195c62d3eee1c7b9318e60a6ac3596430a3de74a987d", "generation_seconds_batch": 25.10575114598032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8392748832702637, "target_z": 0.392578114587031, "ce": 5.772419452667236, "genuineness": 4.494794845581055, "identity": 0.2613537907600403, "hypothesis": "De deur 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_Emotional_Numbness/8a59f753700aff9f6262dff4a179b7a185db37a7c46c7b4e401444d84066f984.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "8a647d89a868fc23d91ac8dbf387953569112d48794f56e393698cdf2d02ccf5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "519b661bc6efa2341f8af75cf2dfbb11391119f1002387813376e2ce1245ea45", "generation_seconds_batch": 17.940340842003934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6073587536811829, "target_z": 0.1513672106264777, "ce": 5.530168056488037, "genuineness": 4.65797233581543, "identity": 0.6733380556106567, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8a647d89a868fc23d91ac8dbf387953569112d48794f56e393698cdf2d02ccf5.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "8a91505d956a2c3af5b5d2ecbc8e03a8e7f71a1b0a6883cecaf1884c260e50fe", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5d3faf711e8bbff1aafba13ae622190292f283f27bd314adea5a0357cb94a231", "generation_seconds_batch": 29.09519086498767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6937404870986938, "target_z": 0.24121096595404323, "ce": 5.279973983764648, "genuineness": 4.557555198669434, "identity": 0.7165443897247314, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8a91505d956a2c3af5b5d2ecbc8e03a8e7f71a1b0a6883cecaf1884c260e50fe.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "8a9be3207adc4721be67ab7101d74961801178383646f91585d6675935a444f7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "df1498c01dd13b4cf281f69b40bca7605023365b8e1269b92464c5c167cf0a4b", "generation_seconds_batch": 23.1093726020772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17075541615486145, "target_z": -0.3027343902562104, "ce": 6.284721851348877, "genuineness": 4.582659721374512, "identity": 0.589906632900238, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8a9be3207adc4721be67ab7101d74961801178383646f91585d6675935a444f7.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "8ae8c47c10a0088fc335985928696d77883af0ac0ee32f5deb42a43aaed331a6", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4f9b650340a6e22bae662c341ad8aaa5f59dc866d5b109d29787b5e342c883e6", "generation_seconds_batch": 15.808669785037637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24211424589157104, "target_z": -0.2285156291167552, "ce": 6.078212261199951, "genuineness": 4.256305694580078, "identity": 0.743590235710144, "hypothesis": "De deur 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_Emotional_Numbness/8ae8c47c10a0088fc335985928696d77883af0ac0ee32f5deb42a43aaed331a6.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": "8b89adaa17121694fa96fa92fa223ddea758df930ba34a70bc6d2899504da80f", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "448c42f62fc6df69bae46e3fb8bda1c3e09956eb0b061a773734732479952ab3", "generation_seconds_batch": 16.406469826004468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4984426498413086, "target_z": 0.038085948518374185, "ce": 6.006728172302246, "genuineness": 4.770940780639648, "identity": 0.6726886034011841, "hypothesis": "Jamand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8b89adaa17121694fa96fa92fa223ddea758df930ba34a70bc6d2899504da80f.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "8b98d54e0114c49febdf7c10a8d10aa9a2fde2c761f05d410ee829710a13fa2b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "dc1d37ce846047a0efd164d07803617390615926c12da8157b784c57cadd472d", "generation_seconds_batch": 26.418593921000138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06371721625328064, "target_z": -0.4140624854702758, "ce": 6.372091293334961, "genuineness": 4.457139015197754, "identity": 0.35088109970092773, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8b98d54e0114c49febdf7c10a8d10aa9a2fde2c761f05d410ee829710a13fa2b.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "8c23949d89f054f8380f859de4200c7abb00967d83f715f995dff3fc1c9e00ef", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "eb47cfe01bc0c41ae5fe9836147f84aecf9f6e4c9fc3a778c188f8001bcb03c2", "generation_seconds_batch": 23.00942736095749, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9838703870773315, "target_z": 0.5429687417664896, "ce": 5.617537498474121, "genuineness": 4.507347106933594, "identity": 0.6659930944442749, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8c23949d89f054f8380f859de4200c7abb00967d83f715f995dff3fc1c9e00ef.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "8c9b78185397045abd568e6d0a6b63436b71b1918a2cb831a5e66972754e811c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "35ca2273a3d6dceab1eebf915166c0d21a68896362e349b83c59ff1df7385655", "generation_seconds_batch": 18.887540284078568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6928015351295471, "target_z": 0.24023438250702417, "ce": 5.847874641418457, "genuineness": 4.319066047668457, "identity": 0.6280436515808105, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8c9b78185397045abd568e6d0a6b63436b71b1918a2cb831a5e66972754e811c.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": "8ce71072e64a2783801dba4ffea0e8ad8f9e4d4de20952398e03026aa6a2c7a9", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "771254bbb9a99783ff93a70b5ff9e0de0ad58d0a1bb2ccf1d3d1108b8504ba94", "generation_seconds_batch": 18.566232717013918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7904504537582397, "target_z": 0.3417968912248587, "ce": 5.839932441711426, "genuineness": 4.457139015197754, "identity": 0.6183739900588989, "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_Emotional_Numbness/8ce71072e64a2783801dba4ffea0e8ad8f9e4d4de20952398e03026aa6a2c7a9.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "8d411f51208a304c85beebad27bf92448406544a5fbdf8e35b5a8ce4a2140141", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a32eb4e19bc5b45a3ed0987b988b9cc445486e178ea8ebb708d46943f23f1a49", "generation_seconds_batch": 18.687050367007032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3791983127593994, "target_z": -0.08593748353297924, "ce": 5.95112943649292, "genuineness": 4.909013748168945, "identity": 0.7968205213546753, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu 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_Emotional_Numbness/8d411f51208a304c85beebad27bf92448406544a5fbdf8e35b5a8ce4a2140141.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "8d57c8a3f1c1dab9c743146414274f798b33a9913ec878c852aaf28df32eb21b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c8984a27f878024453cf7e6c4428fc2d699f50af4123355252ea60e946f8c99c", "generation_seconds_batch": 22.924465373973362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2684043347835541, "target_z": -0.2011718815383759, "ce": 6.046441555023193, "genuineness": 4.796044826507568, "identity": 0.7377779483795166, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8d57c8a3f1c1dab9c743146414274f798b33a9913ec878c852aaf28df32eb21b.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": "8d58e952032417850fbd84f28292695cc2088a18f7cfce6f60a88372f91e1a9e", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "394558a418932161a48f1ad0cf79b368db06f5cec5775f8b89dcc1304193edd8", "generation_seconds_batch": 25.046935116988607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0402063131332397, "target_z": 0.6015625087178346, "ce": 6.070269584655762, "genuineness": 4.7458367347717285, "identity": 0.7076401710510254, "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_Emotional_Numbness/8d58e952032417850fbd84f28292695cc2088a18f7cfce6f60a88372f91e1a9e.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "8d8779eed423a6e784bf9ec899e45190b26f7ba05a84239132083af5c9b4a273", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ffee63a6da36ddc68b682e7ceb28b3ff4d729f666850484c3208ff0447a851b3", "generation_seconds_batch": 24.718666234984994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24211424589157104, "target_z": -0.2285156291167552, "ce": 6.062326908111572, "genuineness": 4.381826400756836, "identity": 0.8159130811691284, "hypothesis": "De deur 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_Emotional_Numbness/8d8779eed423a6e784bf9ec899e45190b26f7ba05a84239132083af5c9b4a273.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "8d8ef64adf9361ae992b1c4bee2e444e741e5b27730f5026a4db64ae1914c462", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "bf66eb84c5f551a4cad541d051c57b3be0ac437af3d45d1603d4ed1433d685c2", "generation_seconds_batch": 25.80477549904026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44058096408843994, "target_z": -0.02209472778844548, "ce": 5.474569320678711, "genuineness": 4.507347106933594, "identity": 0.6291230916976929, "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": 0.120000000000001, "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_Emotional_Numbness/8d8ef64adf9361ae992b1c4bee2e444e741e5b27730f5026a4db64ae1914c462.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "8dcc7d093347efbf45825096d5b3665fc8381a4ff9c47997500e7487a6a1aa5c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "79a8aba45a77c8a02b4b1e53189b9fa920933118e87aa5b09e9def785f104b7b", "generation_seconds_batch": 23.174628773937002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47743403911590576, "target_z": 0.01623535109331099, "ce": 5.502368927001953, "genuineness": 4.758388519287109, "identity": 0.36170846223831177, "hypothesis": "De deur 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_Emotional_Numbness/8dcc7d093347efbf45825096d5b3665fc8381a4ff9c47997500e7487a6a1aa5c.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": "8de27f04384b6fb550b0443e4ffb30c52320f19c633254f995a8ddd6e8b76f80", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bedd91a0a081742cc910e9070a650cd9c8062dbaf92076e4428dffd77268d3b0", "generation_seconds_batch": 24.422542501008138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5712098479270935, "target_z": 0.11376952283486806, "ce": 5.522225379943848, "genuineness": 4.68307638168335, "identity": 0.53485107421875, "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_Emotional_Numbness/8de27f04384b6fb550b0443e4ffb30c52320f19c633254f995a8ddd6e8b76f80.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "8e2ca26e4ecc1e1adcc187be0ef7665f822fab7aaf2620b0426ee2aade218f9c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7549f5b823d3df92ba350a82abbbbacfa5ae9d98fd1a59bebae4b9f57557d9da", "generation_seconds_batch": 21.763379907002673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30314481258392334, "target_z": -0.16503906891729486, "ce": 5.708878040313721, "genuineness": 4.519899368286133, "identity": 0.7046175003051758, "hypothesis": "La porte 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_Emotional_Numbness/8e2ca26e4ecc1e1adcc187be0ef7665f822fab7aaf2620b0426ee2aade218f9c.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "8eda0d2c0b2ef2178758643238ed4cb86e09c775048c5ff4c89b77324f9e8171", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "046ada7c8afd6e934f3a3ac03a372c1587940471c7352779c7974e3e185b9658", "generation_seconds_batch": 24.64245597901754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6815343499183655, "target_z": 0.2285156291167552, "ce": 5.871703147888184, "genuineness": 4.7834930419921875, "identity": 0.6896545886993408, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/8eda0d2c0b2ef2178758643238ed4cb86e09c775048c5ff4c89b77324f9e8171.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "8ef1a5504fead40294c09bb3dffb594f9d4246b12898ddd2011e91e6f5f1f118", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ce15262d0172bda14bebae72fd0e51716f74bb2448f01aedfee7d12df3b788be", "generation_seconds_batch": 25.325565358041786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32943493127822876, "target_z": -0.1376952903421706, "ce": 5.720792293548584, "genuineness": 4.582659721374512, "identity": 0.845780611038208, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/8ef1a5504fead40294c09bb3dffb594f9d4246b12898ddd2011e91e6f5f1f118.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "8f0010a7dcee530559e87ba16bcbbb7026b3e16f505c56bc8c46da8ab6ad8f2b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3ab6943f9461594c2ac8802bdc5d3644311afdc081dad3485689f8a3beb706c5", "generation_seconds_batch": 23.860751954023726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1951676607131958, "target_z": -0.2773437475783793, "ce": 6.1894097328186035, "genuineness": 4.457139015197754, "identity": 0.47435909509658813, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/8f0010a7dcee530559e87ba16bcbbb7026b3e16f505c56bc8c46da8ab6ad8f2b.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": "8f02a6d84ee3f1a41099f638c16575498c289ec35420f86749f158ef07f2c907", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b169a1ceff2d6e845de5060d9080bff276356180cad139fa12b5b9dd46f19977", "generation_seconds_batch": 26.98023581900634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24962569773197174, "target_z": -0.22070313202270003, "ce": 5.272031307220459, "genuineness": 4.494794845581055, "identity": 0.6306633949279785, "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_Emotional_Numbness/8f02a6d84ee3f1a41099f638c16575498c289ec35420f86749f158ef07f2c907.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "8f0e3366d15063605b04292936cfccbc741d958310dd1942488042ab0cdc2f1b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6b6447b056397b8a19e3f6d6d95525bc30e30918b14e9db15069edcaff92d063", "generation_seconds_batch": 25.05612519197166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29375550150871277, "target_z": -0.1748046864102707, "ce": 5.982900142669678, "genuineness": 4.7081804275512695, "identity": 0.7987926006317139, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/8f0e3366d15063605b04292936cfccbc741d958310dd1942488042ab0cdc2f1b.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "8f47f740264ca0aa2d2be709d6968c3d6bcee64b85656033e07c99048a2e9667", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2537681389888b16a70a74e9902590a369d7034982206be4ff64d503a37fff9a", "generation_seconds_batch": 16.80917611590121, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13695389032363892, "target_z": -0.3378906194302724, "ce": 6.1894097328186035, "genuineness": 4.607763767242432, "identity": 0.5760729312896729, "hypothesis": "La porte 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_Emotional_Numbness/8f47f740264ca0aa2d2be709d6968c3d6bcee64b85656033e07c99048a2e9667.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "8f85cc780aee2f3529af84d2e94559d4ca51a6a5a28e4a4f032d8d27eb714bf7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ee121266d52ff6300d5cf37c1b785b3b1836ba232d739994faa896e3e046d184", "generation_seconds_batch": 23.03477882198058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14258748292922974, "target_z": -0.3320312427351379, "ce": 6.062326908111572, "genuineness": 4.406930446624756, "identity": 0.7703723311424255, "hypothesis": "Ik 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_Emotional_Numbness/8f85cc780aee2f3529af84d2e94559d4ca51a6a5a28e4a4f032d8d27eb714bf7.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "90091ab77a41909d1610e2ce208ffd377acecbd67220751acecdedd06a8f1dc7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0293f46f93dc3446523ed2551baeb072c0d77f74eeeda6f1d4806e589d3b5f86", "generation_seconds_batch": 23.65951520006638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6984351277351379, "target_z": 0.24609375920215867, "ce": 5.80021858215332, "genuineness": 4.7081804275512695, "identity": 0.8492118120193481, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/90091ab77a41909d1610e2ce208ffd377acecbd67220751acecdedd06a8f1dc7.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "9028cc3d291168620ea8080027eefba2383a6253a88800a8287c935fbdcce1c6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb4bde3f314dff853414d189fd7802bce98f3cad520fdb56263cc6a519a5f34c", "generation_seconds_batch": 18.875411252025515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18577834963798523, "target_z": -0.28710936507135515, "ce": 5.927301406860352, "genuineness": 5.034534454345703, "identity": 0.6599924564361572, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9028cc3d291168620ea8080027eefba2383a6253a88800a8287c935fbdcce1c6.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "90494a4f7c007a9a744a427f73c498a8873e95d0cfbd17809c9459cd47366efc", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "371d04124cb6f44aa908bbefd343107468a75fbefbd7eeb9afc1f1a763a0af53", "generation_seconds_batch": 23.149232438066974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07874011993408203, "target_z": -0.3984374912821655, "ce": 6.300607204437256, "genuineness": 4.557555198669434, "identity": 0.5135117769241333, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/90494a4f7c007a9a744a427f73c498a8873e95d0cfbd17809c9459cd47366efc.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "90b19fbcfddbcbfc978f619407955c991121765b4d2603c632aebc7a31caf5b7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e30aab23e48c80e67473f39b1d3f24c052a2c50d047b0f48b1a37fb7813d17b3", "generation_seconds_batch": 18.811271913000382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12005311250686646, "target_z": -0.35546874951567586, "ce": 6.165581703186035, "genuineness": 4.532451152801514, "identity": 0.6588097810745239, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/90b19fbcfddbcbfc978f619407955c991121765b4d2603c632aebc7a31caf5b7.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "90d224850f480ab5d605af6ebc87f2d6d487fd67673bb0051483ba7431c60696", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dc70cea41f3a6f49e7c970ebfc3fd82f233b398adee7f4a217832ff90af4ff8f", "generation_seconds_batch": 21.89081387303304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28342723846435547, "target_z": -0.18554688735026556, "ce": 5.967014789581299, "genuineness": 4.457139015197754, "identity": 0.6368075013160706, "hypothesis": "Ik 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_Emotional_Numbness/90d224850f480ab5d605af6ebc87f2d6d487fd67673bb0051483ba7431c60696.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "919f43781fd700439a9e3193cc1adc0c4cda8bfc3e542bcae071cbe8b8fe869f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4b1ccdbc078703cd4c047ede5292effdd401828c0b3fcf7df5ce6efa80516d3a", "generation_seconds_batch": 21.995316607994027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27497684955596924, "target_z": -0.1943359523929673, "ce": 5.871703147888184, "genuineness": 4.256305694580078, "identity": 0.2719545364379883, "hypothesis": "The 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_Emotional_Numbness/919f43781fd700439a9e3193cc1adc0c4cda8bfc3e542bcae071cbe8b8fe869f.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "9330a1d9d5a2849295b431831332685653bbc75dc7dc2968167970ac99b7bf73", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ef556ef13fb444be18fa6210de648643fbc3b418853418cfc08c76de2f114093", "generation_seconds_batch": 24.417032472090796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.766038179397583, "target_z": 0.3164062175502826, "ce": 5.661221981048584, "genuineness": 4.607763767242432, "identity": 0.6335019469261169, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9330a1d9d5a2849295b431831332685653bbc75dc7dc2968167970ac99b7bf73.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "933f7b47f793e5aa218350890fd5eb547b11ab55adfbeced82ade1f32a34b34b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eab27a6bc36d20bfeaa85d3a8d7b8a55232706d6e04043f8f07343c61bbd01e5", "generation_seconds_batch": 22.9121555009624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1313202977180481, "target_z": -0.34374999612540685, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.8564106225967407, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/933f7b47f793e5aa218350890fd5eb547b11ab55adfbeced82ade1f32a34b34b.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "93596fd4d837977ccaa028eee28006dd04ab7acf7571cfc8ab3814cd17dc4b53", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ed90d44a0ff11259cb34a410c3bbbb9385d50765faa79a2b36ca7a32559ed8b0", "generation_seconds_batch": 23.367059231968597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17638900876045227, "target_z": -0.29687501356107593, "ce": 6.23706579208374, "genuineness": 4.293961524963379, "identity": 0.29497891664505005, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/93596fd4d837977ccaa028eee28006dd04ab7acf7571cfc8ab3814cd17dc4b53.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "93952a8b8cfb56463c0bfe25f75c8ab738fdf3140006fed147132fcea0d91c7d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5eab35aa7f2247964a76167cb1f099fd6b342eae965f0d66e4e7f77514686a73", "generation_seconds_batch": 24.34381599293556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2993890941143036, "target_z": -0.1689453097151362, "ce": 5.831989288330078, "genuineness": 4.356721878051758, "identity": 0.6564037203788757, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/93952a8b8cfb56463c0bfe25f75c8ab738fdf3140006fed147132fcea0d91c7d.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "93e41877537316fabaa8bf508f89807b4b0f9c1750f9e7f301dafe4684172f50", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fea994351bc298c9a545e9e00af3bf8aa4e2386c67322eeceb601c435343b22", "generation_seconds_batch": 24.28032120305579, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6036030054092407, "target_z": 0.14746093883189137, "ce": 5.696964263916016, "genuineness": 4.3127899169921875, "identity": 0.5191580653190613, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/93e41877537316fabaa8bf508f89807b4b0f9c1750f9e7f301dafe4684172f50.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "956dbc744ec535cd7d39236bdfba8e56367e6b0b9139e3cec15b0743c7159fee", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8d7e71f3c7f5f29305bce3012e72e5b2901764007a74feec3da01c064ff77da4", "generation_seconds_batch": 23.897109190002084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24211424589157104, "target_z": -0.2285156291167552, "ce": 5.935244083404541, "genuineness": 4.557555198669434, "identity": 0.704657793045044, "hypothesis": "La porte 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_Emotional_Numbness/956dbc744ec535cd7d39236bdfba8e56367e6b0b9139e3cec15b0743c7159fee.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "95e1b09cc5f6c3964e8b20818c2dc46aac6a8b92c75790141ec7df033f00f74c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fd5e2bd64ba5003d12b2cc24e6a3f552474c17917101e6b25785e9f10e593d86", "generation_seconds_batch": 24.026338972966187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10690805315971375, "target_z": -0.369140638803238, "ce": 6.2767791748046875, "genuineness": 4.469690799713135, "identity": 0.2020099014043808, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/95e1b09cc5f6c3964e8b20818c2dc46aac6a8b92c75790141ec7df033f00f74c.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "95fd21713fb88a71e403dd60fbb5fe091ba90c5abe722d2245302861c8405b9f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1017f25ef9c4284eed40620c74afc3a1867f7eea2cd3ef78a79465b35b648a0d", "generation_seconds_batch": 23.607172866002657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0176719427108765, "target_z": 0.5781250019372965, "ce": 5.422942161560059, "genuineness": 4.319066047668457, "identity": 0.5618863105773926, "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_Emotional_Numbness/95fd21713fb88a71e403dd60fbb5fe091ba90c5abe722d2245302861c8405b9f.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "968aef6847cbf128372ab6d939bf4ab5f8045072289c498f1d717cbc26f34bb0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8d34417d390e7dcb704ac6dec15ac0eab20df1fbc77e73e80d361c2b0e52c8ee", "generation_seconds_batch": 26.15057247201912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5214464664459229, "target_z": 0.06201171602567671, "ce": 5.796247482299805, "genuineness": 4.7081804275512695, "identity": 0.7074359655380249, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/968aef6847cbf128372ab6d939bf4ab5f8045072289c498f1d717cbc26f34bb0.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "968c9c77587588eac526db4583d9b3a83a3d61821d32608b95d2bdafcfc920a2", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e707f1bf44e7d057d3d2cacc6e759643fe9e1a225834fe7b99e8923ed117cdb", "generation_seconds_batch": 18.069172856980003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.215824156999588, "target_z": -0.2558593766951345, "ce": 6.157639026641846, "genuineness": 4.457139015197754, "identity": 0.8079580068588257, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/968c9c77587588eac526db4583d9b3a83a3d61821d32608b95d2bdafcfc920a2.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "96c50ffd010a8f314868ca25df6b375f97fec16a62448b380488ca0fa7a0ff55", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cedfb06935fc08d79cc2de4ac7b36024cb17e2741c4ca2925b507f17c00c1cef", "generation_seconds_batch": 25.252448305953294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20643484592437744, "target_z": -0.2656249941881103, "ce": 5.796247482299805, "genuineness": 4.15588903427124, "identity": 0.38884323835372925, "hypothesis": "The 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_Emotional_Numbness/96c50ffd010a8f314868ca25df6b375f97fec16a62448b380488ca0fa7a0ff55.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": "96ebbe0266eee9120c58e71a5873ab2baf246fa4d786afbbac91f4fedd5f30ce", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "2d70ca005d73a7f421529de461577cd6cf946e564281382b952d6a52dff9c592", "generation_seconds_batch": 19.441564140026458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5059540867805481, "target_z": 0.045898430114056865, "ce": 5.895530700683594, "genuineness": 4.6956281661987305, "identity": 0.7504022121429443, "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_Emotional_Numbness/96ebbe0266eee9120c58e71a5873ab2baf246fa4d786afbbac91f4fedd5f30ce.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "97044b6eb8ed6efe24ea48917ddf51a2f3ee08af60d4e2b7d737e8f4d91889aa", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d8f11c1d8ce0dbc6ba7c2d074cfd55a8885dd3b3578fc70d6885ea2e3d76bd42", "generation_seconds_batch": 18.302908636978827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1519767940044403, "target_z": -0.32226562524216207, "ce": 6.205295085906982, "genuineness": 4.65797233581543, "identity": 0.2606116533279419, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/97044b6eb8ed6efe24ea48917ddf51a2f3ee08af60d4e2b7d737e8f4d91889aa.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "9719ef4a153dfb68c5848437ebe4c108512286d2be2eb2629df920af8072c24f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a1b3e8d505cf7ffa47ae682cbd75e0068471fa5e241b8b6285e66cc3ae2110b7", "generation_seconds_batch": 23.58705886802636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6571221351623535, "target_z": 0.20312501743566905, "ce": 5.784333229064941, "genuineness": 4.507347106933594, "identity": 0.5679253935813904, "hypothesis": "De deur 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_Emotional_Numbness/9719ef4a153dfb68c5848437ebe4c108512286d2be2eb2629df920af8072c24f.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": "97246135c40c91b1ce082e2b22bae5195e35d587dca8163ff1ee7d5111a1a086", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The road turns left behind the bridge.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f4ea7f3fa2dd847ebaf04516356f69d8e1133d36adf5b94741ba8f9f9db7cab0", "generation_seconds_batch": 18.92086409800686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4686315655708313, "target_z": 0.007080090505535833, "ce": 6.316492557525635, "genuineness": 4.494794845581055, "identity": 0.40893980860710144, "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_Emotional_Numbness/97246135c40c91b1ce082e2b22bae5195e35d587dca8163ff1ee7d5111a1a086.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "97708d407ca934965a4c782ff8654144e9f0b57ea734f5d101d4a60582f39a4b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b6c282ea9b866b1949ef2c8fa201dc31de1d619ca9564a7c0f2a9eb41ae74963", "generation_seconds_batch": 18.567844754084945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5895190238952637, "target_z": 0.13281249709405515, "ce": 5.839932441711426, "genuineness": 4.557555198669434, "identity": 0.6608335971832275, "hypothesis": "De deur 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_Emotional_Numbness/97708d407ca934965a4c782ff8654144e9f0b57ea734f5d101d4a60582f39a4b.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "97e9dafdfa583686e25093ca7282a06bd929611c20a6a81dff38567c3a0c3c5a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0c10c7bff895d270cd5a2a926c131902a7b40acfcabeff7d0f5a3a514bc04a39", "generation_seconds_batch": 24.567669773008674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29845017194747925, "target_z": -0.16992186216541028, "ce": 5.6334228515625, "genuineness": 4.557555198669434, "identity": 0.5877178907394409, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/97e9dafdfa583686e25093ca7282a06bd929611c20a6a81dff38567c3a0c3c5a.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "98eb8df6b302e899a97e5df57b0084775567c2da9cc735801408c049bcf40688", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1045492db1c64a2b5699332daf87039236ddbd1a0b7df257d49ae03b9a905981", "generation_seconds_batch": 18.811271913000382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10878592729568481, "target_z": -0.3671875029059448, "ce": 6.141753673553467, "genuineness": 4.3881025314331055, "identity": 0.47680342197418213, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/98eb8df6b302e899a97e5df57b0084775567c2da9cc735801408c049bcf40688.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "990eaea8ef058514e2b560dbaafa75a5472c8ed42f1c16e8525c73fc58985c34", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a432a89157f15cac8ca81b5019aab6b442542a54fe684713da265adeba5587b9", "generation_seconds_batch": 25.458198643988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45654281973838806, "target_z": -0.0054931501533161, "ce": 5.9431867599487305, "genuineness": 5.034534454345703, "identity": 0.8577234745025635, "hypothesis": "La porte 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_Emotional_Numbness/990eaea8ef058514e2b560dbaafa75a5472c8ed42f1c16e8525c73fc58985c34.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "991195cbccfce76be91e37d3339d64823a7c9b61dec8a881364320e2b3e2a143", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ec050154392b687dc6fb7c1972bfdcb71ba9fc3327b10165eedc4ea87503d8cc", "generation_seconds_batch": 24.86101613100618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5791907906532288, "target_z": 0.12207032715080524, "ce": 5.974957466125488, "genuineness": 4.833701133728027, "identity": 0.6823011636734009, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/991195cbccfce76be91e37d3339d64823a7c9b61dec8a881364320e2b3e2a143.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "993c74e983d7fda9f9c30d6bf946a31658b1bbcf9deab81e0051c85d5d24c485", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "72cdc48fb998542272d0e16c1e4f0edbf09cf3e6fa6b1d9884fe5d8f056b265e", "generation_seconds_batch": 25.43380811798852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1594882607460022, "target_z": -0.3144531126497344, "ce": 5.927301406860352, "genuineness": 4.507347106933594, "identity": 0.6953036785125732, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/993c74e983d7fda9f9c30d6bf946a31658b1bbcf9deab81e0051c85d5d24c485.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "9945cf2a9dcb3f817d0689d23812d0d696ea674a71fd8c6359a49a255785cae4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c7898e4b0dd667bc62713ccb10f43d74fe7f0bf7b795da9abb8a37f7a9fc1a3d", "generation_seconds_batch": 25.90426329395268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24023638665676117, "target_z": -0.23046874951567586, "ce": 5.935244083404541, "genuineness": 4.344170093536377, "identity": 0.38008254766464233, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9945cf2a9dcb3f817d0689d23812d0d696ea674a71fd8c6359a49a255785cae4.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "14e3fc829ad3d30cd572a6031f042a57246894d1bf4510e606c0e6d11cac2202", "generation_seconds_batch": 18.271035377983935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06935077905654907, "target_z": -0.40820313977188627, "ce": 6.41180419921875, "genuineness": 4.595211505889893, "identity": 0.47383663058280945, "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_Emotional_Numbness/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "99dea8c6c662b0a5001dde2ab3e3b4891f7d23bfb922b60e34a0471e24f93521", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ab913ec82e678e200cd0d107bff64c2eae12be74e83d068532e5012c1cee6e2c", "generation_seconds_batch": 24.690965460031293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2918776273727417, "target_z": -0.17675782230756384, "ce": 5.863759994506836, "genuineness": 4.174716949462891, "identity": 0.5925782918930054, "hypothesis": "Ik 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_Emotional_Numbness/99dea8c6c662b0a5001dde2ab3e3b4891f7d23bfb922b60e34a0471e24f93521.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "9b4c7890f789d9c33278b61f5283dc36195fe320a0b32b8d70c6925fd84439c1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eadb29d8baa20ea4039a2b5ee77622f8bec22ad553dd687c9336b343f1026d44", "generation_seconds_batch": 22.97360586898867, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20831269025802612, "target_z": -0.26367188928756213, "ce": 6.141753673553467, "genuineness": 4.306513786315918, "identity": 0.22850991785526276, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9b4c7890f789d9c33278b61f5283dc36195fe320a0b32b8d70c6925fd84439c1.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "9b52bda9b16fec86107fbd9a0f6069c0ab51e0d483ae769b9c793ef326ad67de", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2af7b9351248ebdcc251ab39b4367d878835fc83f7ff20128266517a28fcc817", "generation_seconds_batch": 23.952000466990285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4396420419216156, "target_z": -0.02307128023871957, "ce": 6.117925643920898, "genuineness": 4.934117794036865, "identity": 0.5426712036132812, "hypothesis": "La porte 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_Emotional_Numbness/9b52bda9b16fec86107fbd9a0f6069c0ab51e0d483ae769b9c793ef326ad67de.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "9ba2a528827eb613b8002dee0f08b7be3ab29dbdb790fc210e2678079562e19e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "44314cb6a5db46393a6689f876b5c774fa0eda5fd15cdb41e376dcb0cb084e3c", "generation_seconds_batch": 26.14811315399129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1313202977180481, "target_z": -0.34374999612540685, "ce": 5.974957466125488, "genuineness": 4.319066047668457, "identity": 0.25057125091552734, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9ba2a528827eb613b8002dee0f08b7be3ab29dbdb790fc210e2678079562e19e.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "6af436f2155da3b910a0a9ac982bc79ef2f48eba88cc30f24958af6128778149", "generation_seconds_batch": 19.5456306389533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16512185335159302, "target_z": -0.30859373595459993, "ce": 6.173524379730225, "genuineness": 4.406930446624756, "identity": 0.7224425673484802, "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_Emotional_Numbness/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "9c4de376cb8a92ab86a206043fa2c1d730decfe2581ddb5ab2fade6e47518d42", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3f373ca81b43fc2ede763197d4ac36d146ea53e1d2b5a9e7fa698898a6ec532b", "generation_seconds_batch": 19.187318479060195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09376302361488342, "target_z": -0.3828124970940552, "ce": 6.316492557525635, "genuineness": 4.381826400756836, "identity": 0.4403226673603058, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9c4de376cb8a92ab86a206043fa2c1d730decfe2581ddb5ab2fade6e47518d42.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "9c585506b7bfe238549568555625ec70b7a9071fa16f511d8a5860c86a0885a3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c95fc1e0d4896914125a1abd07ba0b358ca3628bb59d31e051928b742626997f", "generation_seconds_batch": 25.71544219891075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05057215690612793, "target_z": -0.42773437475783793, "ce": 6.4912309646606445, "genuineness": 4.582659721374512, "identity": 0.3007323741912842, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9c585506b7bfe238549568555625ec70b7a9071fa16f511d8a5860c86a0885a3.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "9c687297620f4cc5646de568217fec27a6bc5c4d3e5b6b85f02c66db2914fe76", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "113eed5a8118041e4fdcd21380dca171b984716c4356a9274731b5a481ebbd86", "generation_seconds_batch": 21.995316607994027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23648065328598022, "target_z": -0.2343750058118897, "ce": 6.054384231567383, "genuineness": 4.381826400756836, "identity": 0.29407617449760437, "hypothesis": "The 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_Emotional_Numbness/9c687297620f4cc5646de568217fec27a6bc5c4d3e5b6b85f02c66db2914fe76.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "9c853643830f2277bf243eaaf7ef4cc472d43a47db4fa429f02b141ba79db973", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f9b0639f4c8906cfacbaa0b51a6c0a95742ed981f6f78f5996b9f1c7a0aaf099", "generation_seconds_batch": 25.633277017972432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15009891986846924, "target_z": -0.32421876113945525, "ce": 6.284721851348877, "genuineness": 4.570107460021973, "identity": 0.7270324230194092, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9c853643830f2277bf243eaaf7ef4cc472d43a47db4fa429f02b141ba79db973.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "c978e0b7945cf21ef1c0a77b7d01cbdcc1f75804983bd95409ef90d829a415cb", "generation_seconds_batch": 17.43373608693946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33412957191467285, "target_z": -0.13281249709405515, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.6603018045425415, "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_Emotional_Numbness/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "9cfeee06508712d3a92aeb9a53cf5073cd61c86a8edd422ed3d5a8672a8576f3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ae741640112a33cd8e9ae034176d6f4e52b469bf07731f86f034311918f69027", "generation_seconds_batch": 24.29099760495592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5467976331710815, "target_z": 0.08837891115378192, "ce": 5.569881439208984, "genuineness": 4.582659721374512, "identity": 0.6864063143730164, "hypothesis": "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_Emotional_Numbness/9cfeee06508712d3a92aeb9a53cf5073cd61c86a8edd422ed3d5a8672a8576f3.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "9d2ee02af5baec654fe461b0534e43e04dea6424d92ddec9e1cff8e2c9c247e0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bdd34b08af1564a7104b6a13bdbac50e56e04ec2e0c64f6ef295f253072e6691", "generation_seconds_batch": 18.624280560063198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2233356088399887, "target_z": -0.24804687960107932, "ce": 6.109982967376709, "genuineness": 4.469690799713135, "identity": 0.20675094425678253, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9d2ee02af5baec654fe461b0534e43e04dea6424d92ddec9e1cff8e2c9c247e0.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "9df77441ffa9bc3ef5c3798c5918ae0119258ec3c095cad94f6b12aa7f24c378", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9d5a93f0260a33921b338b49134c4e76079e405bcd29aefd74d3be953fa6ee32", "generation_seconds_batch": 23.877591513912193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43752944469451904, "target_z": -0.025268546499395004, "ce": 6.09409761428833, "genuineness": 4.632867813110352, "identity": 0.4949270486831665, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9df77441ffa9bc3ef5c3798c5918ae0119258ec3c095cad94f6b12aa7f24c378.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": "9e7bfa0f55bd67adbe097ded50937aef8883e1e1e030498cc02d13cd71e4abbb", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59a56e4e16bcbffd9e63943701a1d6d8b3476e6d6c5afa0c9500580b9e058f50", "generation_seconds_batch": 24.84624436905142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34586620330810547, "target_z": -0.12060548297702162, "ce": 5.982900142669678, "genuineness": 4.808597087860107, "identity": 0.8922763466835022, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lass 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_Emotional_Numbness/9e7bfa0f55bd67adbe097ded50937aef8883e1e1e030498cc02d13cd71e4abbb.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "9ebe48fcb85bd179ade55064bbef6e5ccef42cb6b6cde075b22494cfb8876fcd", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b90ecf9162895da465a389ce1aac1f0c6ef31f1e1d4687869f7fe072347b727", "generation_seconds_batch": 23.367059231968597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1519767940044403, "target_z": -0.32226562524216207, "ce": 5.9431867599487305, "genuineness": 4.20609712600708, "identity": 0.38555586338043213, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9ebe48fcb85bd179ade55064bbef6e5ccef42cb6b6cde075b22494cfb8876fcd.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "9ed3a91eed21fa3a40f7a0e1f9a668f17613d46519a63a9ef292b7f1e99a0471", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "940bb8a61785073191c4aa45c0336f893793bdd260267a1bdae9a3e072310acc", "generation_seconds_batch": 21.56451441394165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21957989037036896, "target_z": -0.25195312039892065, "ce": 6.205295085906982, "genuineness": 4.607763767242432, "identity": 0.6731462478637695, "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_Emotional_Numbness/9ed3a91eed21fa3a40f7a0e1f9a668f17613d46519a63a9ef292b7f1e99a0471.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "9ed79d18b015700b232f90bf5cc6c49474844fd0ebf752de402c7ea454506fd9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4986219be89fb9a71f503581cd70c8dcd4e8715b56e3e82ad550b0d9c16e3b98", "generation_seconds_batch": 25.88394180999603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2561982274055481, "target_z": -0.21386718737891897, "ce": 5.8875885009765625, "genuineness": 4.507347106933594, "identity": 0.3703378140926361, "hypothesis": "De deur 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_Emotional_Numbness/9ed79d18b015700b232f90bf5cc6c49474844fd0ebf752de402c7ea454506fd9.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "9ed86a2511942fd9a06ca41492f3bc5fb5c739ed21d4e7dd2dd79e4a4a44a829", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "17be80a0f54ab9e01992ae8871fcf73df6fb78331bfeb6503404b0fe3b953a3d", "generation_seconds_batch": 24.88019399798941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29375550150871277, "target_z": -0.1748046864102707, "ce": 5.895530700683594, "genuineness": 4.770940780639648, "identity": 0.7930335998535156, "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_Emotional_Numbness/9ed86a2511942fd9a06ca41492f3bc5fb5c739ed21d4e7dd2dd79e4a4a44a829.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "9edf0c74c306ca2473fe102ddf14f77c85900aa3ff466f3e4b2181a2a9d92417", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0c91be742fec571434c0c354dfc7d5ab0d88b3bb5862876b84f0eb16be4cb9e7", "generation_seconds_batch": 15.659033166011795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3125341534614563, "target_z": -0.15527342042757405, "ce": 5.77639102935791, "genuineness": 4.65797233581543, "identity": 0.5412529110908508, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9edf0c74c306ca2473fe102ddf14f77c85900aa3ff466f3e4b2181a2a9d92417.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "9f3c97f03c832ebe1882e36e7ed330b9cc376918a6cbdd4ec66b7cd51a5f6434", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8122668e77944e4c64b0203df40acbb6ca2a6e9c69307de6d356c02df461ec47", "generation_seconds_batch": 16.79622072901111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08437371253967285, "target_z": -0.392578114587031, "ce": 6.268836498260498, "genuineness": 4.65797233581543, "identity": 0.6443253755569458, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/9f3c97f03c832ebe1882e36e7ed330b9cc376918a6cbdd4ec66b7cd51a5f6434.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "9f71755c57d34b890114c0ef42dbabe145601ec114c88f58036f71ea01c112b8", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "32b5c4542aae86019ce1b17a715d7902d62e4a8ab4e34eba3876622bc56d6b91", "generation_seconds_batch": 25.68143981695175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22896920144557953, "target_z": -0.24218750290594485, "ce": 6.086154937744141, "genuineness": 4.607763767242432, "identity": 0.7515065670013428, "hypothesis": "La porte 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_Emotional_Numbness/9f71755c57d34b890114c0ef42dbabe145601ec114c88f58036f71ea01c112b8.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "9fb7b53f63d855721750dc19df5dd0482ccaab4470b9dfdd272ed1d52e14c004", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "be843cbb6505f3d4b083d4b85a1a2be89bd0d1c4efd3cbafbd64a278bc3dedcd", "generation_seconds_batch": 20.3815203019185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5223854184150696, "target_z": 0.06298829947269577, "ce": 5.792276382446289, "genuineness": 4.821148872375488, "identity": 0.846290111541748, "hypothesis": "La porte 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_Emotional_Numbness/9fb7b53f63d855721750dc19df5dd0482ccaab4470b9dfdd272ed1d52e14c004.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "9fc01444d6367cbb9ef8a97bbc40c251b77a2fda881e8fa8543637b21725f6cd", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0bb7cfe84c43676b592c42b5b97990f5cb0261f04b2f769a799ed91094f9703c", "generation_seconds_batch": 18.567844754084945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3275570273399353, "target_z": -0.13964845723620872, "ce": 5.831989288330078, "genuineness": 4.519899368286133, "identity": 0.6254463195800781, "hypothesis": "De deur staat nog open. Ik heb je Jals op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9fc01444d6367cbb9ef8a97bbc40c251b77a2fda881e8fa8543637b21725f6cd.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": "9fd63b8373bf60c5db1f40da078428ee814335a92e56bb1c694295bbb44c7f90", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "57aef9e62df32d6c91618805b81cf3430ec3a6c8dd05668d07d8a9ad1ed57541", "generation_seconds_batch": 18.532203266979195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5580648183822632, "target_z": 0.1000976645440509, "ce": 5.772419452667236, "genuineness": 4.507347106933594, "identity": 0.647172212600708, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/9fd63b8373bf60c5db1f40da078428ee814335a92e56bb1c694295bbb44c7f90.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "a0289c1b4e9e5aa8c272bd6fda1df1a1c6044d8630a846202c56cb9a1b89ece6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7dddc996638dfde2ef2f92b779dbcb72639aa01d70e72d3c998c3d4d7a031fa2", "generation_seconds_batch": 23.524230194976553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23272493481636047, "target_z": -0.23828124660973102, "ce": 5.9431867599487305, "genuineness": 4.432034492492676, "identity": 0.4976118206977844, "hypothesis": "De deur 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_Emotional_Numbness/a0289c1b4e9e5aa8c272bd6fda1df1a1c6044d8630a846202c56cb9a1b89ece6.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "a04c1c63d7f1c2e5d6e3d15c6cccb8bc46c77e618ec624fbbdbc993cb213ff56", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "95b04fb9a0fb7e036da415c4f545139881d2122b89352edeb69091dcf5d4195f", "generation_seconds_batch": 18.51876401808113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5989083647727966, "target_z": 0.14257814558377596, "ce": 5.609594821929932, "genuineness": 4.7458367347717285, "identity": 0.6997275948524475, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/a04c1c63d7f1c2e5d6e3d15c6cccb8bc46c77e618ec624fbbdbc993cb213ff56.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "a096f8d9921f3e43b1fb47c9ea9a485cba9f9b8afddae33061b735e44c3e47d4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d5517ccd9db32ce11b99edd6cfac016be97463306df2d72f1f7d430a1d07718", "generation_seconds_batch": 18.376792559982277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5801296830177307, "target_z": 0.12304684860433436, "ce": 5.8875885009765625, "genuineness": 4.545003414154053, "identity": 0.7808880805969238, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/a096f8d9921f3e43b1fb47c9ea9a485cba9f9b8afddae33061b735e44c3e47d4.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "a1132465aa3808e4329ba0ac3b776ae0a01edc1209d3504dedb832e60ab811a3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c5577885e77e9060e53b681be94d5b7fd4cb5c6540b7359a76e240827c56de6b", "generation_seconds_batch": 22.873861578991637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6871679425239563, "target_z": 0.2343750058118897, "ce": 6.125868320465088, "genuineness": 4.632867813110352, "identity": 0.5800994634628296, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/a1132465aa3808e4329ba0ac3b776ae0a01edc1209d3504dedb832e60ab811a3.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": "a1699e861bd709195125c5e394905837282344a93343648923b7e3ea05b1859d", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "acf1f9c3753d80638955cdc2914e305b77690f4b0bd985d343ba2a2b5ed54033", "generation_seconds_batch": 25.231431950000115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.641160249710083, "target_z": 0.1865234088037947, "ce": 5.808161735534668, "genuineness": 4.68307638168335, "identity": 0.5777196884155273, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/a1699e861bd709195125c5e394905837282344a93343648923b7e3ea05b1859d.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "a1ebfa6ef261efaf90e4e3e38370c6bea6b180c0348c90e71965fb37bd155324", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3149e737c4a2dcf26ef05cc26da680beb83c394cabff1b114bfc1fc3b5a88923", "generation_seconds_batch": 18.750645297928713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1951676607131958, "target_z": -0.2773437475783793, "ce": 6.109982967376709, "genuineness": 4.7332844734191895, "identity": 0.779988169670105, "hypothesis": "La porte 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_Emotional_Numbness/a1ebfa6ef261efaf90e4e3e38370c6bea6b180c0348c90e71965fb37bd155324.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "a22410de79790236ad873819fbaa5942cb1cc98dfa5d6850205402db3702d982", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d2884cf1c23aa34e54788332b4b9ea42639fc711bcd7a5df47cd4c69ed4f300c", "generation_seconds_batch": 20.30322896700818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21394629776477814, "target_z": -0.2578124970940552, "ce": 6.173524379730225, "genuineness": 4.796044826507568, "identity": 0.6317997574806213, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/a22410de79790236ad873819fbaa5942cb1cc98dfa5d6850205402db3702d982.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "a2a07a4bc5a92450df8e017ac6493500c1058a4b7af2a599a7eada1a2f70bc00", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "33207563b74b0c2aba42b44a02ae6b63d603bbac0b83d34d095c5bd404f00912", "generation_seconds_batch": 25.325565358041786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27028220891952515, "target_z": -0.19921874564108275, "ce": 5.597680568695068, "genuineness": 4.645420074462891, "identity": 0.731778085231781, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/a2a07a4bc5a92450df8e017ac6493500c1058a4b7af2a599a7eada1a2f70bc00.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "a2dce51a91cb2de3d95bb85a7d216180b9ec3d27affa3f1b7ff17d10964c010a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d5d192ecb5c0c041c4df8057b258f9a6699e002d553b7a1688632cac900c1510", "generation_seconds_batch": 23.318626050953753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.674022912979126, "target_z": 0.2207031475210725, "ce": 5.538110733032227, "genuineness": 4.413206577301025, "identity": 0.7320713996887207, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/a2dce51a91cb2de3d95bb85a7d216180b9ec3d27affa3f1b7ff17d10964c010a.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": "a323e95d10542146687042deacc7da80d875a401aee069070bd33ce144e37bab", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Your message arrived after I had left.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "38ca094f397b06dc627c43d83807e87cccec80df35d7e8b0ba46d64b20c5f4d3", "generation_seconds_batch": 22.199890058021992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6280152201652527, "target_z": 0.17285155051297754, "ce": 6.205295085906982, "genuineness": 4.582659721374512, "identity": 0.3263804316520691, "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_Emotional_Numbness/a323e95d10542146687042deacc7da80d875a401aee069070bd33ce144e37bab.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "a4171e535ef25c27c639566ee58757eb2ef6436a25b3f620105fd0ff43c5a66f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2a7a8c897be56c90b9828455a3eb90f661e96069ddf33cc9e64e18177c9adc47", "generation_seconds_batch": 24.022381752962247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4779035151004791, "target_z": 0.01672364281682052, "ce": 5.863759994506836, "genuineness": 4.494794845581055, "identity": 0.6856304407119751, "hypothesis": "De deur 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_Emotional_Numbness/a4171e535ef25c27c639566ee58757eb2ef6436a25b3f620105fd0ff43c5a66f.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": "a48eeb0ae789fac1c7a1ab5d582e729c23caf16a66ff24ec59489ca0495e91b2", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d77ceb1ae9eb77e0f15d3ebcf3adc02276c41f13dcf21b1b29f68fda2e513208", "generation_seconds_batch": 25.357384431990795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29093870520591736, "target_z": -0.17773437475783793, "ce": 5.8875885009765625, "genuineness": 4.65797233581543, "identity": 0.6943669319152832, "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_Emotional_Numbness/a48eeb0ae789fac1c7a1ab5d582e729c23caf16a66ff24ec59489ca0495e91b2.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "a4e6268f68964399fa9419f758804dca6ded935f475b6ac63e4cb1666fa2d8da", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0d03b911ca762bf481e5d316566a8360668519034348e7055b3b54773adab9aa", "generation_seconds_batch": 25.090135145001113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3853013515472412, "target_z": -0.07958984611108018, "ce": 5.232317924499512, "genuineness": 4.607763767242432, "identity": 0.7108696699142456, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/a4e6268f68964399fa9419f758804dca6ded935f475b6ac63e4cb1666fa2d8da.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "a6e84c2230c759fc700491aa7df2a67e11324d253f120853edd63006e1b315a2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a73e76300071010444de4c2a409fcd44a589d3e9f44c98771da53f9fea9f445c", "generation_seconds_batch": 21.40593752101995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22521348297595978, "target_z": -0.24609374370378617, "ce": 5.6413655281066895, "genuineness": 4.7332844734191895, "identity": 0.6933291554450989, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/a6e84c2230c759fc700491aa7df2a67e11324d253f120853edd63006e1b315a2.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "a70dcbb5e1c7767deb38707abd80be73da52cc8bac73a69c8c3074b266c2e4fa", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cb8fd43d6da59d2fca347b4a4b8e0a2e40f5fcbcd93cfbfcca9472a3405bb568", "generation_seconds_batch": 18.24210263893474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9650917649269104, "target_z": 0.5234375067805379, "ce": 5.9431867599487305, "genuineness": 4.808597087860107, "identity": 0.7750874757766724, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/a70dcbb5e1c7767deb38707abd80be73da52cc8bac73a69c8c3074b266c2e4fa.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "a8664ceddcad2b4dcbcbd955280ef5af31f83ca67d5fb8d940c71c86f7439027", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "393f0e4a7af89e187c1c697a2d42414a398c2ef336ab534ce9433d7810054d9c", "generation_seconds_batch": 19.30635125900153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13695389032363892, "target_z": -0.3378906194302724, "ce": 6.157639026641846, "genuineness": 4.570107460021973, "identity": 0.5159547328948975, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/a8664ceddcad2b4dcbcbd955280ef5af31f83ca67d5fb8d940c71c86f7439027.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "a86c4494637b52dc71f6545473c25f68dee8f7fc0dae45437641e4035c026876", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b77f577e7c6a976e1b38e96615255db81c3ead623e8c8cda27206d1e8fa54b9a", "generation_seconds_batch": 24.912094573955983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5805991888046265, "target_z": 0.12353517132458887, "ce": 5.895530700683594, "genuineness": 4.808597087860107, "identity": 0.6729830503463745, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/a86c4494637b52dc71f6545473c25f68dee8f7fc0dae45437641e4035c026876.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "a8a32b35db3a9979b7dcd7d896c1880966b0f9abde87418f2b0afd1e0b9c5583", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "256e5645f1d25b016d5826ff716fbea924d083d9e10bba8c5fa23f5a43eebac9", "generation_seconds_batch": 24.069222026038915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4869407117366791, "target_z": 0.026123033767977956, "ce": 6.1894097328186035, "genuineness": 4.7834930419921875, "identity": 0.7375749349594116, "hypothesis": "La porte 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_Emotional_Numbness/a8a32b35db3a9979b7dcd7d896c1880966b0f9abde87418f2b0afd1e0b9c5583.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "a8ad63064ebbe35cc17e80882127bb331aa6b3518b0c14a0ddbc199a51961d8d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b2b9a55e4ae6654b8df0e3e2fff40489add78f23264eab5cbe11a35512b770d8", "generation_seconds_batch": 19.201657262048684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30032801628112793, "target_z": -0.1679687572648621, "ce": 6.022613525390625, "genuineness": 4.796044826507568, "identity": 0.6986660957336426, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/a8ad63064ebbe35cc17e80882127bb331aa6b3518b0c14a0ddbc199a51961d8d.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "313a672140e81c7632b253650591ae4866438523a37ee3743d38cd9785e37e0d", "generation_seconds_batch": 19.330069506075233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11254164576530457, "target_z": -0.3632812621081035, "ce": 6.292664527893066, "genuineness": 4.444586753845215, "identity": 0.6742496490478516, "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_Emotional_Numbness/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "5f1f62127f274b1af5782966d72e93b4f2a6dd5bef24254134fd8746b64cea34", "generation_seconds_batch": 18.422360655036755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10690805315971375, "target_z": -0.369140638803238, "ce": 6.292664527893066, "genuineness": 4.570107460021973, "identity": 0.7743098139762878, "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_Emotional_Numbness/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "aa3e0dc9da9a4aafe6e46c91bc188053ad787edc519d3f0b56693d60d157dba9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6b20fa41899bff0f14752d15bf36028220bbebbe1eeb2155dc0994bd7f4e22f7", "generation_seconds_batch": 25.85750816296786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5031372904777527, "target_z": 0.04296874176648962, "ce": 5.522225379943848, "genuineness": 4.607763767242432, "identity": 0.5166389346122742, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/aa3e0dc9da9a4aafe6e46c91bc188053ad787edc519d3f0b56693d60d157dba9.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": "aa8d728799fb67ab70606d2fa8b49f6c177036a6673bac84712110f46c3a69fe", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b9b0a424b1353090dd371b5af9bca092d64b2967b2c447e73d5615978bbb1d9", "generation_seconds_batch": 24.84624436905142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36652272939682007, "target_z": -0.09912108109703184, "ce": 5.871703147888184, "genuineness": 4.607763767242432, "identity": 0.6834629774093628, "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_Emotional_Numbness/aa8d728799fb67ab70606d2fa8b49f6c177036a6673bac84712110f46c3a69fe.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "869cea26914260532df4edf3bfbcc11485cf67047e4cfd8cd6a380c72fea3b8e", "generation_seconds_batch": 18.305927093024366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09939661622047424, "target_z": -0.37695312039892065, "ce": 6.443574905395508, "genuineness": 4.042920112609863, "identity": 0.4782600402832031, "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_Emotional_Numbness/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "ab9bf07e38928273c91407d421113845013e7ba86da1919788fbf374df2084d3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "007bb198e8b67bc17cc1ae609338c9341694f8646493baaa29f49835ecb05d75", "generation_seconds_batch": 24.718666234984994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13695389032363892, "target_z": -0.3378906194302724, "ce": 6.006728172302246, "genuineness": 4.469690799713135, "identity": 0.4355213940143585, "hypothesis": "De deur staat nog open. Ik heb jas op de stoel gelegd. Zeg maar, wanneer je. Zeg maar je geleerd Juk en niet.", "wer": 0.42105263157894735, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ab9bf07e38928273c91407d421113845013e7ba86da1919788fbf374df2084d3.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "abfd28f3f832876b198245cb261382b6b8a1fa0661cf378e0219ef31edbfdf60", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "64bb3e8c6df10e3938334d012458b434934acf5e155de9c09e3c183c721079bd", "generation_seconds_batch": 22.89118132099975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1951676607131958, "target_z": -0.2773437475783793, "ce": 5.808161735534668, "genuineness": 4.262581825256348, "identity": 0.7461227178573608, "hypothesis": "La porte 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_Emotional_Numbness/abfd28f3f832876b198245cb261382b6b8a1fa0661cf378e0219ef31edbfdf60.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "ad0e5acb1dfdee8a8b4c63a79d668cb139ef3b0b4933475385447d5ac74145f5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8dcc8d9218f9cc9383d928876199a8ddf55ae2f8baee040f6411b6cd44eb6812", "generation_seconds_batch": 22.701952985022217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38342350721359253, "target_z": -0.08154295101162837, "ce": 5.982900142669678, "genuineness": 4.507347106933594, "identity": 0.5734070539474487, "hypothesis": "Ik 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_Emotional_Numbness/ad0e5acb1dfdee8a8b4c63a79d668cb139ef3b0b4933475385447d5ac74145f5.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "ad426ac2105d05aefb5572618b29826a7ec8ca624a4c7520bf1604396c6a86a6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "399732b2a5fa31e8b03090e9d0f0234c2ac04b32361ac75c5c7277a934a27536", "generation_seconds_batch": 24.864924479974434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19892337918281555, "target_z": -0.27343750678053796, "ce": 6.284721851348877, "genuineness": 4.607763767242432, "identity": 0.43495339155197144, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ad426ac2105d05aefb5572618b29826a7ec8ca624a4c7520bf1604396c6a86a6.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "ad643c85d7472407684694fa6ce7836e66f08cbf2f2ef15606ee0b076b3a2fda", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff5da06e8f502e7f9b0ff4e41c3e303612cad522e9ec956ccee0dbfdaf945d31", "generation_seconds_batch": 17.775689291069284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4118261933326721, "target_z": -0.052001937172573634, "ce": 5.871703147888184, "genuineness": 4.7081804275512695, "identity": 0.4529899060726166, "hypothesis": "De deur 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_Emotional_Numbness/ad643c85d7472407684694fa6ce7836e66f08cbf2f2ef15606ee0b076b3a2fda.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "63fc743830259707e0c9532852b04ab86cb5f3d3e0345f5a7dfe1481fa54b10c", "generation_seconds_batch": 19.167552428902127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.103152334690094, "target_z": -0.37304687960107935, "ce": 6.070269584655762, "genuineness": 4.306513786315918, "identity": 0.5332438349723816, "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_Emotional_Numbness/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "addb20e20d9f3de54550efd33416e746933d408bfea334effeaaa91439904e8f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "16d0d949eea46bdfa8b96e924845523997e1344087c9a034da2e61f2ead01ef2", "generation_seconds_batch": 25.492491937009618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15573251247406006, "target_z": -0.3183593844443207, "ce": 6.316492557525635, "genuineness": 4.607763767242432, "identity": 0.5222779512405396, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/addb20e20d9f3de54550efd33416e746933d408bfea334effeaaa91439904e8f.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "adf27e6f19f5b0c7db9078fd4b448438757c5622af27cd19eac541e6cc2295eb", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a6ccd264be87cc0c3c0b9b7b47c447d46e9095644924858bb38b8f3ebc58d889", "generation_seconds_batch": 24.347672760952264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19328978657722473, "target_z": -0.27929688347567244, "ce": 6.181467056274414, "genuineness": 4.482243061065674, "identity": 0.5723352432250977, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/adf27e6f19f5b0c7db9078fd4b448438757c5622af27cd19eac541e6cc2295eb.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "7827cb76dcb457e247c3a2e76a078544d12a2365241b86b381e27ab0033f941c", "generation_seconds_batch": 17.70674896100536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19328978657722473, "target_z": -0.27929688347567244, "ce": 6.3641486167907715, "genuineness": 4.268857479095459, "identity": 0.3184756338596344, "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_Emotional_Numbness/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "ae8683143f762a65d81704dd30c53f9e7f87faa424f6918cce0cba42b7592736", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e2d6c0f70721933e35605fd65b33e5b2db68c15e422ef1bed64449b2790e4530", "generation_seconds_batch": 23.5798362250207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6205037832260132, "target_z": 0.16503906891729486, "ce": 5.839932441711426, "genuineness": 4.011539936065674, "identity": 0.5040338039398193, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ae8683143f762a65d81704dd30c53f9e7f87faa424f6918cce0cba42b7592736.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "af64b9dfa9d62c695297e2cb1a29ddc28ec32abd6aa5852a8c64fd6aab700f63", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e9fa381dabf5b0aa56b79ac57603f7afef70b681cef1554acc869481a77d1879", "generation_seconds_batch": 23.607172866002657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6796565055847168, "target_z": 0.226562524216207, "ce": 5.696964263916016, "genuineness": 4.482243061065674, "identity": 0.6168104410171509, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/af64b9dfa9d62c695297e2cb1a29ddc28ec32abd6aa5852a8c64fd6aab700f63.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "af722a19167d527dcf8123af17fafea0252398271c9391548ed508b25653a9c3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "147581d51a269ee4e064c4fb426fa36b270ff7b2c836cb0f658b7519eee09c76", "generation_seconds_batch": 23.916368031990714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5979694128036499, "target_z": 0.1416015621367569, "ce": 6.125868320465088, "genuineness": 4.519899368286133, "identity": 0.7547781467437744, "hypothesis": "Ik 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_Emotional_Numbness/af722a19167d527dcf8123af17fafea0252398271c9391548ed508b25653a9c3.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "afb021ceab6fdbd1d9849420eadbda8cbdf822b8269699b4578823286eb683d6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1c5269200775e57ccf34f491bbb47f376dd7a3d500ae72d9521f6d7a3c9a2d8a", "generation_seconds_batch": 23.81642697704956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2177020162343979, "target_z": -0.25390625629621383, "ce": 6.109982967376709, "genuineness": 4.362998008728027, "identity": 0.739940881729126, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/afb021ceab6fdbd1d9849420eadbda8cbdf822b8269699b4578823286eb683d6.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "b017c0a75ff594e2e64e9b88fab52c815151f02f1d839f27b92eab25d8d0aedf", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4ced8ea59b372021af8f9c09e8cb00bc9298e258cad9735e1581750716b2da0c", "generation_seconds_batch": 25.43380811798852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2233356088399887, "target_z": -0.24804687960107932, "ce": 6.125868320465088, "genuineness": 4.6956281661987305, "identity": 0.7598024606704712, "hypothesis": "J'ai trouvé la petite boîte, elle était près de 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_Emotional_Numbness/b017c0a75ff594e2e64e9b88fab52c815151f02f1d839f27b92eab25d8d0aedf.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "b078aff55ad6e57b5c0ef15e3ac08fc98ffd675e809ea8247e008930e5ab2fc6", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "49c2b49234413dc2f89591a515ede9f00ed7b3f91ff6753de9b56b997f0bcbd8", "generation_seconds_batch": 16.860299329971895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09939661622047424, "target_z": -0.37695312039892065, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.8270351886749268, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b078aff55ad6e57b5c0ef15e3ac08fc98ffd675e809ea8247e008930e5ab2fc6.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "b0b58627146eccabae790c5efd98b550f1528fbde7d853a3482b23c8596c7c69", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "aa5ba08e077bfa813daeccabd8ce5643b6dae6155bd1d57d7e6453ea6d1a0e89", "generation_seconds_batch": 25.306314384914003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7021908760070801, "target_z": 0.25000003099674495, "ce": 5.80021858215332, "genuineness": 4.632867813110352, "identity": 0.68505859375, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b0b58627146eccabae790c5efd98b550f1528fbde7d853a3482b23c8596c7c69.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "b1d8196dc4b51dcb194ad011082c3c85e658c2109d6df5ba20e0ba48bbdc0df5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ac083c1e733f72653cc6fdfd4ed50eab7b670270788240c2e3532d851bf16754", "generation_seconds_batch": 26.019981432007626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4928090572357178, "target_z": 0.0322265718232397, "ce": 6.149696350097656, "genuineness": 4.570107460021973, "identity": 0.7032471299171448, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b1d8196dc4b51dcb194ad011082c3c85e658c2109d6df5ba20e0ba48bbdc0df5.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "b1dc56af5ab1f5bd8d7998d0e83a4c084b694e6876f6c35b2424ee8144596389", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "def9d1539e62b3d7e473a5f9c3e428876034eab789d046569a9d4aedbe9bdf5b", "generation_seconds_batch": 23.174628773937002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38624030351638794, "target_z": -0.07861326266406111, "ce": 6.006728172302246, "genuineness": 4.381826400756836, "identity": 0.4542430639266968, "hypothesis": "De deur 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_Emotional_Numbness/b1dc56af5ab1f5bd8d7998d0e83a4c084b694e6876f6c35b2424ee8144596389.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "b1e5c7aebc5c1e23e658a46a2e7d3616164f41e69d261d0a2b869cd6b863880f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "439baf32c323f605d6ca63f0e31d512617bcee8e28797d62c478301cdc1025cf", "generation_seconds_batch": 18.537311463966034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8880993127822876, "target_z": 0.4433593379492033, "ce": 5.442798614501953, "genuineness": 4.68307638168335, "identity": 0.6298214793205261, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b1e5c7aebc5c1e23e658a46a2e7d3616164f41e69d261d0a2b869cd6b863880f.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "b22154e437e3180be055a993e8fdab21f6ffa43ed61f96f27b9a338000328b2f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "869d531da5ccc6499ec23a8f62ced477487d4f98f16ee5b212224aa076ed45d2", "generation_seconds_batch": 24.738524249987677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3679311275482178, "target_z": -0.09765623692324822, "ce": 5.879645347595215, "genuineness": 4.8588056564331055, "identity": 0.7883061170578003, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b22154e437e3180be055a993e8fdab21f6ffa43ed61f96f27b9a338000328b2f.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": "b22d5055e4bb674095c49e3d3116558c5de12280ae556b3db42cd0c008cbff5e", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "c37588ff2c574aaa576c80799a418b5125e6f2c560126c27752119ab8df59cbf", "generation_seconds_batch": 18.588305870071054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5698014497756958, "target_z": 0.11230467866108444, "ce": 6.046441555023193, "genuineness": 4.65797233581543, "identity": 0.614423930644989, "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_Emotional_Numbness/b22d5055e4bb674095c49e3d3116558c5de12280ae556b3db42cd0c008cbff5e.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": "b231d77219b9c58cfdeef89761400b8856c2792d0f1cebcdcd6edbee1b5ba833", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c9c5694ae3dfc6bb5354133e843df362eea10be5c3b433082945173af12ddbc", "generation_seconds_batch": 23.041774076991715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8035954833030701, "target_z": 0.35546874951567586, "ce": 5.510311126708984, "genuineness": 4.369274139404297, "identity": 0.35106968879699707, "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_Emotional_Numbness/b231d77219b9c58cfdeef89761400b8856c2792d0f1cebcdcd6edbee1b5ba833.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "b276eae7062e1834d81190ce5732597e2d1aec19bf09fd1fc4ce9db0d30c94d1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7b2a775a98282bd73a43c0117f4c094ffbd56b81a2ac5492996912055fee9240", "generation_seconds_batch": 23.57447907293681, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3932822644710541, "target_z": -0.07128907279188798, "ce": 6.038498878479004, "genuineness": 4.595211505889893, "identity": 0.5644447803497314, "hypothesis": "De deur 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_Emotional_Numbness/b276eae7062e1834d81190ce5732597e2d1aec19bf09fd1fc4ce9db0d30c94d1.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "b2975289129086d49394a82bd4442dcfa1aa04f6b2e78b3423ddf8a53c1ba98f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "92f25ac6df97dd2467823642b3b675ac05ead041843db48440806cced5a9672b", "generation_seconds_batch": 24.021391859976575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15761038661003113, "target_z": -0.3164062485470276, "ce": 5.982900142669678, "genuineness": 4.7458367347717285, "identity": 0.6964836120605469, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b2975289129086d49394a82bd4442dcfa1aa04f6b2e78b3423ddf8a53c1ba98f.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "b2c6b67ae33d3aced0e7899165f24febdc2282ff65c62179dde0c4355b8d51b3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b72c4e70f9e13afa479c5be89b58c50f1411266b521268f3b55d74a9534449bb", "generation_seconds_batch": 24.443554840050638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30596160888671875, "target_z": -0.16210938056972762, "ce": 5.982900142669678, "genuineness": 4.7458367347717285, "identity": 0.5418375730514526, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b2c6b67ae33d3aced0e7899165f24febdc2282ff65c62179dde0c4355b8d51b3.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "b31f897cf738195a0ceb623e47512e6bc0b1772f2fcb98a336cbdfb10bee82a0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a71c4c18c1f3bb07f2868ef288b23e4b89e84ec98089a6c03c0733ef8f0ffa0d", "generation_seconds_batch": 27.13431357999798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5383472442626953, "target_z": 0.07958984611108018, "ce": 5.9431867599487305, "genuineness": 4.632867813110352, "identity": 0.799309253692627, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b31f897cf738195a0ceb623e47512e6bc0b1772f2fcb98a336cbdfb10bee82a0.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "b385ed86f00143da4ca697d3755463b34a43d309a91e90c88d5d552e2ecc87eb", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "43540ae60949ebd6e92d936ee3c16654bd409dd692ab55f30f24c4fc7cf07d8b", "generation_seconds_batch": 24.912094573955983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4706267714500427, "target_z": 0.009155260587775157, "ce": 6.062326908111572, "genuineness": 4.758388519287109, "identity": 0.7101057767868042, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b385ed86f00143da4ca697d3755463b34a43d309a91e90c88d5d552e2ecc87eb.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "b3db1405956e8414a15ce5019edd20cf26246a15abeb5c96f19a70da593e9aec", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "31bac44395f820215a5a6873969296924b3844f8a4fe568bae5bc49b1b99799c", "generation_seconds_batch": 24.920484559959732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17075541615486145, "target_z": -0.3027343902562104, "ce": 6.09409761428833, "genuineness": 4.68307638168335, "identity": 0.5655161142349243, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b3db1405956e8414a15ce5019edd20cf26246a15abeb5c96f19a70da593e9aec.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "b3fccd9b697571298ab885cd5dc75bc77b6a7cb14163058020c7e1538c61b568", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3f60c27c11f8e896b3268f844f85cf7bd6767bcf6d9b9b9ab7fbedcd7efcda60", "generation_seconds_batch": 17.003160982974805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10503020882606506, "target_z": -0.37109374370378617, "ce": 6.300607204437256, "genuineness": 4.545003414154053, "identity": 0.4599493145942688, "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_Emotional_Numbness/b3fccd9b697571298ab885cd5dc75bc77b6a7cb14163058020c7e1538c61b568.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "4de31a1b3c1a042d34ef0e433823b5bf21eaf44e8d3bb7b676889373773a7644", "generation_seconds_batch": 17.36467011703644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12193098664283752, "target_z": -0.3535156136183827, "ce": 6.316492557525635, "genuineness": 4.143336772918701, "identity": 0.5760518312454224, "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_Emotional_Numbness/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "b44b4d408719fcc74bdd20c3aecb8ecd603da92a5ebe5c9b7c42fbf9bcbcccee", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "81a02c155f69e7a2bd98abe76a7a0f2e28cd80719d157381279e66f701c1cafc", "generation_seconds_batch": 24.391875973087735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29375550150871277, "target_z": -0.1748046864102707, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.47275862097740173, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b44b4d408719fcc74bdd20c3aecb8ecd603da92a5ebe5c9b7c42fbf9bcbcccee.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "b47aba01265e1550f44e5385314a9ac3e2ed3b10f4c66c16bf6feae8ccd9b105", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "899e4a0dcbe1b26703dcbd84323dbb5b8fa0f4ae357f7e34cb49d9b3a08d123d", "generation_seconds_batch": 22.86744919209741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7134580612182617, "target_z": 0.26171878438701396, "ce": 5.935244083404541, "genuineness": 4.507347106933594, "identity": 0.28579992055892944, "hypothesis": "Ik 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_Emotional_Numbness/b47aba01265e1550f44e5385314a9ac3e2ed3b10f4c66c16bf6feae8ccd9b105.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "b4d29e40cfd500a010072b7b3f4e39955af524109545d9b5f8c06efccaa32049", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2e5788a0f8b6ba0544f120c5020880052bc411f63809214fd66c34406d21b07e", "generation_seconds_batch": 18.387534435023554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38764870166778564, "target_z": -0.0771484184902775, "ce": 6.022613525390625, "genuineness": 4.306513786315918, "identity": 0.49841973185539246, "hypothesis": "Ik 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_Emotional_Numbness/b4d29e40cfd500a010072b7b3f4e39955af524109545d9b5f8c06efccaa32049.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "b4d2e2d7beee6b79c5affff7bef9e2e07c68b5464e5fd28e2dd5fceb3d68871f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7fbcbaf2ce77d23b6b1a13def041660a87ebc1906281a37fdba80ec00a670119", "generation_seconds_batch": 24.391875973087735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3679311275482178, "target_z": -0.09765623692324822, "ce": 6.117925643920898, "genuineness": 4.720732688903809, "identity": 0.380082368850708, "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_Emotional_Numbness/b4d2e2d7beee6b79c5affff7bef9e2e07c68b5464e5fd28e2dd5fceb3d68871f.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "b533aa85240b4c39c8faf0ab65fb9b610cf1253353df651b0c5da4650b16de4c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dfb8bafde2ca4311a505832f3f22a5b7594d598688193f71a36292b827d5e926", "generation_seconds_batch": 18.750645297928713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23178599774837494, "target_z": -0.2392578145583776, "ce": 5.871703147888184, "genuineness": 4.331617832183838, "identity": 0.7125530242919922, "hypothesis": "La porte 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_Emotional_Numbness/b533aa85240b4c39c8faf0ab65fb9b610cf1253353df651b0c5da4650b16de4c.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "b55faaa36d1efac49fa168048170ae488ba3e67163907167c451527ab66d5d4a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d40385ac7d7b5625218589ca4e8cba5afa4013e93e5dac62faa11732ec833267", "generation_seconds_batch": 24.66411050898023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5998472571372986, "target_z": 0.14355466703730507, "ce": 5.542081832885742, "genuineness": 4.796044826507568, "identity": 0.6127414703369141, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b55faaa36d1efac49fa168048170ae488ba3e67163907167c451527ab66d5d4a.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "b5bb131444ac22fc3011d15da3bd4092bc3c50d039c81fe61d1077c4b9fc73d7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3cda4530ea0bd1f97d9afbd6aa6ec3b927cfdfd089fb8ff2924e935ae81e6c4f", "generation_seconds_batch": 26.03815897309687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19328978657722473, "target_z": -0.27929688347567244, "ce": 6.117925643920898, "genuineness": 4.645420074462891, "identity": 0.6857470273971558, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b5bb131444ac22fc3011d15da3bd4092bc3c50d039c81fe61d1077c4b9fc73d7.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "b61a0722c5afb6e479aff762f9f37c851a8698554337a5b521b953a18ecbbde6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "20778d6d6a6ba004d3a414b4861092636c98ea2aa44cd0a70e545a25d885ceb2", "generation_seconds_batch": 21.652356379083358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.289999783039093, "target_z": -0.17871092720811202, "ce": 6.125868320465088, "genuineness": 4.369274139404297, "identity": 0.5541378259658813, "hypothesis": "De deur 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_Emotional_Numbness/b61a0722c5afb6e479aff762f9f37c851a8698554337a5b521b953a18ecbbde6.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": "b647f5c8960df11be0cfee4490a1e3e67c7e241bce8ff302b57e001aaf4d14f9", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7d5c281b4db8ff01ba5421668db0dffdf902cfa1f165ad9a05f4229a96d7870d", "generation_seconds_batch": 17.972596102044918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6552442312240601, "target_z": 0.20117185054163092, "ce": 5.911416053771973, "genuineness": 4.7834930419921875, "identity": 0.6152796149253845, "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_Emotional_Numbness/b647f5c8960df11be0cfee4490a1e3e67c7e241bce8ff302b57e001aaf4d14f9.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "b68dbb82f0a5e540184f2dc5a91d866c2e0e65470ce061bf3662b56835ded6cc", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "891682827974aaa91cb3944924227c2788627f83489ed1b5ac84e8cf13145bb8", "generation_seconds_batch": 23.079374531982467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1876561939716339, "target_z": -0.2851562601708069, "ce": 5.863759994506836, "genuineness": 4.344170093536377, "identity": 0.7203826904296875, "hypothesis": "De deur 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_Emotional_Numbness/b68dbb82f0a5e540184f2dc5a91d866c2e0e65470ce061bf3662b56835ded6cc.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "b73cc337b8b8a342824ded01909300d2c0617be57b0306278f72f3489e900533", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6042d6c50e4e8650fe34297473cf1e970fb43c8ba822cb23414b72805c7d1b0e", "generation_seconds_batch": 25.061987460008822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8449084758758545, "target_z": 0.3984374912821655, "ce": 5.720792293548584, "genuineness": 4.268857479095459, "identity": 0.6171518564224243, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen samen inkijken", "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_Emotional_Numbness/b73cc337b8b8a342824ded01909300d2c0617be57b0306278f72f3489e900533.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "b7a4e492d7b19ac401504a50944767496144241a87d2e07b540c462ebe5f2d41", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1395458eef90af9bf6579bcfecc958215186ff3590beb964921d72f88aaeef59", "generation_seconds_batch": 23.799785634037107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11254164576530457, "target_z": -0.3632812621081035, "ce": 6.229123115539551, "genuineness": 4.168440818786621, "identity": 0.337005615234375, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b7a4e492d7b19ac401504a50944767496144241a87d2e07b540c462ebe5f2d41.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "b7e7864a70af0553d786f39060dc2e3da03fafd98febb5895c73ba177562fa4b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0e67859237ef2391da9047ebc4c5d43620ad50d036f2f91e58bba7461c643b95", "generation_seconds_batch": 23.87188117997721, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5322442054748535, "target_z": 0.07324220868918113, "ce": 5.919358730316162, "genuineness": 4.8588056564331055, "identity": 0.7001352310180664, "hypothesis": "La porte 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_Emotional_Numbness/b7e7864a70af0553d786f39060dc2e3da03fafd98febb5895c73ba177562fa4b.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "b910cfdb5641ef689961921e1277d5485238fc95a980435e5d8425f94f0cb411", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "c3d114dda95b13481d07d9247e3662c3a8b670be1ce3b11e7def626b699d86b7", "generation_seconds_batch": 25.552486127940938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12193098664283752, "target_z": -0.3535156136183827, "ce": 6.205295085906982, "genuineness": 4.532451152801514, "identity": 0.6623526811599731, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/b910cfdb5641ef689961921e1277d5485238fc95a980435e5d8425f94f0cb411.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "b99e4a2a0f942e44c723c020ab0316016047f0ca1791352da1de31d0e74effc4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f395436a50cbd641368db6eccbc50c6f5dd8fd8a0bf1f1fe74501a94f4214898", "generation_seconds_batch": 23.116326601943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5083014369010925, "target_z": 0.04833985773485955, "ce": 5.839932441711426, "genuineness": 4.770940780639648, "identity": 0.8228269815444946, "hypothesis": "La porte 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_Emotional_Numbness/b99e4a2a0f942e44c723c020ab0316016047f0ca1791352da1de31d0e74effc4.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "b9b325491db64e5930d66577f8710d67e5f308d222292dc981279012a13892b4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c85f018e5c8d89001051eaa94f64d1b591dcd75451eefd6c429ac97592b56088", "generation_seconds_batch": 25.393609042977914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4284922182559967, "target_z": -0.034667968447297415, "ce": 5.903473377227783, "genuineness": 4.7458367347717285, "identity": 0.35792750120162964, "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_Emotional_Numbness/b9b325491db64e5930d66577f8710d67e5f308d222292dc981279012a13892b4.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "463fe2d4ea43c8600aa1d09fec21f6b51c50ce814aca83fb5b379b052961688c", "generation_seconds_batch": 18.885165581014007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1820226013660431, "target_z": -0.29101563686594145, "ce": 6.078212261199951, "genuineness": 4.432034492492676, "identity": 0.713185727596283, "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_Emotional_Numbness/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "baae3fb35277e830495c93f42b48705fcfb44be735aef8b73903538ae5cbcea5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e7d91fcea02ad6af9bc1af7a64e6da294f29e0213579c42b83d7a6397296de75", "generation_seconds_batch": 20.437350912950933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.889977216720581, "target_z": 0.4453125048432414, "ce": 5.498397350311279, "genuineness": 4.394378662109375, "identity": 0.2992728650569916, "hypothesis": "De deur 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_Emotional_Numbness/baae3fb35277e830495c93f42b48705fcfb44be735aef8b73903538ae5cbcea5.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": "babfdba581a5e85d0eeeaaac0e85f19a61a6ad9238bde47fb2edde40cc527a7a", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "79432943788c059a29b928c679c959c92b9286e03c7405279b9700fa1b70ae2c", "generation_seconds_batch": 17.972596102044918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42168495059013367, "target_z": -0.04174805895283325, "ce": 5.593709468841553, "genuineness": 4.896461486816406, "identity": 0.6650939583778381, "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_Emotional_Numbness/babfdba581a5e85d0eeeaaac0e85f19a61a6ad9238bde47fb2edde40cc527a7a.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "baf02c95b90438fe214696560c83d6e6af8f16912f1d2472d50eaa8ca9459106", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d8ba0991c98f0502f643b70b948d727235cc4f75cbae5c8dc4a562536541c88e", "generation_seconds_batch": 24.05165428505279, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5188643932342529, "target_z": 0.059326158041491744, "ce": 6.046441555023193, "genuineness": 4.871357440948486, "identity": 0.7294211387634277, "hypothesis": "La porte 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_Emotional_Numbness/baf02c95b90438fe214696560c83d6e6af8f16912f1d2472d50eaa8ca9459106.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "bbfeb9467ac15ba7be273745e423ca4476a8965c8e71191d9e19ce30a09b69cb", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68858018c484be20f66391acad1dd024b48512d5ef38ed55377c958861e8c21f", "generation_seconds_batch": 21.601044927956536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6280152201652527, "target_z": 0.17285155051297754, "ce": 5.95112943649292, "genuineness": 4.720732688903809, "identity": 0.7293004989624023, "hypothesis": "La porte 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_Emotional_Numbness/bbfeb9467ac15ba7be273745e423ca4476a8965c8e71191d9e19ce30a09b69cb.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "bc8e5014d94c04ea041e9e307d7599109ba8ca4f0a149b7f0fa9a2a7ebfd8394", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2d36ef9de2f5ac1e8a2a5b2f5a9a0fddaa7ad41589ff3072af281a5d5376176d", "generation_seconds_batch": 19.187318479060195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11441951990127563, "target_z": -0.36132812621081034, "ce": 6.109982967376709, "genuineness": 4.256305694580078, "identity": 0.4085220694541931, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/bc8e5014d94c04ea041e9e307d7599109ba8ca4f0a149b7f0fa9a2a7ebfd8394.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "bcb9b70b48a961f3446ba83ffe9fe3ef0f910bd604ed3eb52e65ba7625100099", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "251b451bfd19766d0e8ffef5e222ae3d7350a519a3001d7049b2cf2d2429c9c4", "generation_seconds_batch": 22.711115163983777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31159520149230957, "target_z": -0.15625000387459312, "ce": 6.0305562019348145, "genuineness": 4.570107460021973, "identity": 0.47416263818740845, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/bcb9b70b48a961f3446ba83ffe9fe3ef0f910bd604ed3eb52e65ba7625100099.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "bcc275918a79e41da49b25d6c82e0f9354449bf82ae3e4b540467f9b296e0670", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5da9fe53c8001532194915e6d6388d8a03f0ac6bef0e4dba26884f31936f568e", "generation_seconds_batch": 25.652448214939795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3881181478500366, "target_z": -0.07666015776351294, "ce": 5.895530700683594, "genuineness": 4.7834930419921875, "identity": 0.7286558747291565, "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_Emotional_Numbness/bcc275918a79e41da49b25d6c82e0f9354449bf82ae3e4b540467f9b296e0670.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "bd076be1c56d9f6386bc7f637a084a9bc5c8a8c36b461f2efdb2516e3d59ed7c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "76c078d6d7feafd75684b3e9067ec2e4dcbeb5ec79fb12249f509d7ce826f78c", "generation_seconds_batch": 25.63908661797177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5951526165008545, "target_z": 0.13867187378918966, "ce": 5.95112943649292, "genuineness": 4.808597087860107, "identity": 0.7544513940811157, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/bd076be1c56d9f6386bc7f637a084a9bc5c8a8c36b461f2efdb2516e3d59ed7c.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "bd12ad7cc3583788704a9ae9ff23af864fe55763b4b3d25739bbb89e531a0bd0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "07b0a91bacbddb75a8bcee66778e6558b0604355c06ec93d56657822a597aa29", "generation_seconds_batch": 25.88394180999603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24023638665676117, "target_z": -0.23046874951567586, "ce": 6.078212261199951, "genuineness": 4.507347106933594, "identity": 0.5991427898406982, "hypothesis": "De deur 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_Emotional_Numbness/bd12ad7cc3583788704a9ae9ff23af864fe55763b4b3d25739bbb89e531a0bd0.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "bd16c44d96a79caebe38c4546a086786da9710709b5629df625885b88b917476", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "31f851432bb466ba739ecf0a85ecf50d198253c4dd4c0f2f16fadd36f1f70c22", "generation_seconds_batch": 22.14687237504404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6251984238624573, "target_z": 0.16992186216541028, "ce": 6.181467056274414, "genuineness": 4.846253395080566, "identity": 0.897676944732666, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/bd16c44d96a79caebe38c4546a086786da9710709b5629df625885b88b917476.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "bd9340a5ab68d29dfe7acbf5a8a2928525648ba50a0bef3377f686f9293f77fb", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "079ea3140a80a0441cad0b3061190e51763b24ac72b6e4b4277cca5053bdd8f4", "generation_seconds_batch": 20.072934504947625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5155781507492065, "target_z": 0.05590820896715994, "ce": 5.903473377227783, "genuineness": 4.833701133728027, "identity": 0.6241241693496704, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/bd9340a5ab68d29dfe7acbf5a8a2928525648ba50a0bef3377f686f9293f77fb.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": "bdc0930da33a23c45450bb3fe72d50b53993ab91909fceb98b775c0041721c5f", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "4533be42383c020557fc3771587484eb641b4accbdc27c1090f1400ce72a16b8", "generation_seconds_batch": 18.22553607390728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8787100315093994, "target_z": 0.4335937514529724, "ce": 5.577824115753174, "genuineness": 4.7834930419921875, "identity": 0.782822847366333, "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_Emotional_Numbness/bdc0930da33a23c45450bb3fe72d50b53993ab91909fceb98b775c0041721c5f.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "be188c53390e58378a05f158caeee16f1fa76976cbfbc97d9973929ee925d498", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa847070856b176e5959c8e2d424217d7e9807a220deacbf746def700364e7a5", "generation_seconds_batch": 26.468761850963347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1876561939716339, "target_z": -0.2851562601708069, "ce": 5.974957466125488, "genuineness": 4.532451152801514, "identity": 0.732230544090271, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen het er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/be188c53390e58378a05f158caeee16f1fa76976cbfbc97d9973929ee925d498.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": "be8dd1d8846c96d49cb1d32e5a4b3031c26dc3fa919021a904eadde681c5d40b", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3e1082eeb256fcacd52f47804f5e5a499c698552d743bd1585c37968d246731a", "generation_seconds_batch": 24.20789404900279, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7303588390350342, "target_z": 0.27929691447241745, "ce": 5.839932441711426, "genuineness": 4.871357440948486, "identity": 0.6887292861938477, "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_Emotional_Numbness/be8dd1d8846c96d49cb1d32e5a4b3031c26dc3fa919021a904eadde681c5d40b.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "bea49b119685ef93aeb50e79f11ea5547bda38ab6b9e7ce31448b243237b3a11", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "97f2dde5d1f68063522ef4e0051771431302370186b39c7c9f6d7b33e5a6dcd7", "generation_seconds_batch": 26.176872087060474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07122865319252014, "target_z": -0.40625000387459315, "ce": 6.38003396987915, "genuineness": 4.545003414154053, "identity": 0.3277609646320343, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/bea49b119685ef93aeb50e79f11ea5547bda38ab6b9e7ce31448b243237b3a11.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "bebe28880a134213801feadc5c75efcfd04bfbb7055000a8539f882a8fc1e215", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2999ade9b3b5fd3d07249fdefcf34285fd02af7e34ab063e33d1288f64735708", "generation_seconds_batch": 19.06429436604958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2543203830718994, "target_z": -0.21582029227946714, "ce": 6.125868320465088, "genuineness": 4.758388519287109, "identity": 0.6963834762573242, "hypothesis": "La porte 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_Emotional_Numbness/bebe28880a134213801feadc5c75efcfd04bfbb7055000a8539f882a8fc1e215.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "bed0b8e9bcb1b25e928b69f97bf970490616f648f4443ee7ba3504922d0b6e3a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "73d1d3aaa55ee90b509bd52a82d5bcb906f10f03cc56037b25f299d4da98dadd", "generation_seconds_batch": 23.96922260604333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2843661904335022, "target_z": -0.18457030390324652, "ce": 6.181467056274414, "genuineness": 4.532451152801514, "identity": 0.8189216256141663, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/bed0b8e9bcb1b25e928b69f97bf970490616f648f4443ee7ba3504922d0b6e3a.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "bf1f3269117fcb7551eadc43c99715bf4b60491b0b8d6481161a3a43f9872389", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "516cd9a67d6f08e8e2bb586337a108fbdeb63311d9904b3f1ca6db5927b9fd4f", "generation_seconds_batch": 22.867939891992137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12568670511245728, "target_z": -0.3496093728205414, "ce": 6.046441555023193, "genuineness": 4.193545341491699, "identity": 0.24179282784461975, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/bf1f3269117fcb7551eadc43c99715bf4b60491b0b8d6481161a3a43f9872389.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "bfbe00e61f38f12fa92597e695c5ee2cebb373405d18d0e2daa3239135ec6bf8", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "935246bc0b31d40014f1c019f28fa83415727c2b6eb2a73f8570fb9cf9a02093", "generation_seconds_batch": 22.957526177051477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12193098664283752, "target_z": -0.3535156136183827, "ce": 6.252951145172119, "genuineness": 4.582659721374512, "identity": 0.6633428335189819, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/bfbe00e61f38f12fa92597e695c5ee2cebb373405d18d0e2daa3239135ec6bf8.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": "c073a2ede234f6b23b8b012c6c528c822d2f42eb5d048ae67c3619645aa9271e", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "3c44860d44a2406dd2ca478aa3592ac45e2d022ad1114d832394667134e016e8", "generation_seconds_batch": 18.588305870071054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47766876220703125, "target_z": 0.01647948145669327, "ce": 5.895530700683594, "genuineness": 4.406930446624756, "identity": 0.38798844814300537, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten net 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_Emotional_Numbness/c073a2ede234f6b23b8b012c6c528c822d2f42eb5d048ae67c3619645aa9271e.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "c11c3d58b97cc5743266b207add80a59946133e95452a5373918ee586e6a6203", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6e26fcb7a899e2ceda8a07265373fc17f81eb1fccc2fdab61c614ed17e860720", "generation_seconds_batch": 29.53206873999443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30032801628112793, "target_z": -0.1679687572648621, "ce": 5.720792293548584, "genuineness": 4.645420074462891, "identity": 0.5598763227462769, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c11c3d58b97cc5743266b207add80a59946133e95452a5373918ee586e6a6203.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "c13c820567635871288108f78fe89b5bd32c671b43fc2a4285a70e210d892405", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "577ac1dcad18beec59205039ecb6762511ab9d103ffb03cb447a29ceeae38ee2", "generation_seconds_batch": 25.652448214939795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40079373121261597, "target_z": -0.06347656019946034, "ce": 5.744620323181152, "genuineness": 4.582659721374512, "identity": 0.7706278562545776, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c13c820567635871288108f78fe89b5bd32c671b43fc2a4285a70e210d892405.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "c159775887a1bd5b8b4996bf7d74506a38f8259be10d15ea509cca2d62a4ba63", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "455e3164b507118a08e345a6f2e29f0a2e4bdded4d7ef2a1d1195f205d7e564c", "generation_seconds_batch": 24.35756873898208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06559506058692932, "target_z": -0.4121093805697276, "ce": 6.419747352600098, "genuineness": 4.2751336097717285, "identity": 0.582287073135376, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c159775887a1bd5b8b4996bf7d74506a38f8259be10d15ea509cca2d62a4ba63.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "c1c03e16c59382503867a4d9e36aef0e3c56ddb20d268690492a20a9cf0450e4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45e480547adf93c0b9d630583a5a782eb0821afd646a24bf5598e6781aa35bcf", "generation_seconds_batch": 18.61741498496849, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8711985349655151, "target_z": 0.4257812078637998, "ce": 5.935244083404541, "genuineness": 4.406930446624756, "identity": 0.14375311136245728, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude rama. 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_Emotional_Numbness/c1c03e16c59382503867a4d9e36aef0e3c56ddb20d268690492a20a9cf0450e4.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "c1d4d0c371b8235bab6e4fabbe4ca784edde059709fcdb1b7867431ff4b1de33", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a06bcba658c03517af1309b37b935b99bfa66b32e1918ada2f9bee25ed4f0287", "generation_seconds_batch": 22.353348979959264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10503020882606506, "target_z": -0.37109374370378617, "ce": 6.046441555023193, "genuineness": 4.758388519287109, "identity": 0.6735632419586182, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c1d4d0c371b8235bab6e4fabbe4ca784edde059709fcdb1b7867431ff4b1de33.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "c2397e2dcc203e780201a7fc696484823c57a807af6ec1873b9f5e17e9eec3e0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bbab90db1873f61cc1419fc9b38864b2c1b9838551d051e3ee9223a3a43cab62", "generation_seconds_batch": 24.690965460031293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36417537927627563, "target_z": -0.10156250871783452, "ce": 6.078212261199951, "genuineness": 4.381826400756836, "identity": 0.7623457908630371, "hypothesis": "Ik 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_Emotional_Numbness/c2397e2dcc203e780201a7fc696484823c57a807af6ec1873b9f5e17e9eec3e0.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "c2a8c0d2ac84adc1c42ce6976a5f7e026cbab05ff193bb03b3ed48cbcf309339", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "10e37972cc0407027b48da28e7652a2f5d1c4d1be256e1ff351bc0bdea414670", "generation_seconds_batch": 24.75933765002992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37309524416923523, "target_z": -0.09228515195162326, "ce": 5.4825119972229, "genuineness": 4.570107460021973, "identity": 0.5977072715759277, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c2a8c0d2ac84adc1c42ce6976a5f7e026cbab05ff193bb03b3ed48cbcf309339.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "c34147231a1ec80dd29bed182479be040112ffc4cea0fb1ae84476830d3dbf64", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b2ac342bf2838554fe3a173d7ce464bda574640d677a2b5c92945f1ef041c63", "generation_seconds_batch": 24.05165428505279, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3191066384315491, "target_z": -0.14843752227891044, "ce": 5.847874641418457, "genuineness": 4.532451152801514, "identity": 0.7720081210136414, "hypothesis": "La porte 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_Emotional_Numbness/c34147231a1ec80dd29bed182479be040112ffc4cea0fb1ae84476830d3dbf64.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "5895b7f5cec6e67d9bc19f08772e75bf3527bf708ccb2b133b795c5f2c787b97", "generation_seconds_batch": 17.43373608693946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2026791274547577, "target_z": -0.26953123498595166, "ce": 6.062326908111572, "genuineness": 4.444586753845215, "identity": 0.7182396650314331, "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_Emotional_Numbness/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "c3e0b5363f2259df60b42126be9a347ff9efd8f489d9c20c17790f2b20f2de83", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7ebeac812913a2c9856c53460960c6e5deaa674426680ca982d7b3f6f8b55dc7", "generation_seconds_batch": 25.546151370042935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11066380143165588, "target_z": -0.3652343670086517, "ce": 6.340320587158203, "genuineness": 4.2249250411987305, "identity": 0.22599244117736816, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c3e0b5363f2259df60b42126be9a347ff9efd8f489d9c20c17790f2b20f2de83.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "c4171e419ad384ad8198481919b90b470dda82a1dbabb1b824d51a90b5681284", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc41f3ad478db9cd0a6b6b0533881cf9a3ff379d9814c40d7e1961cff463b852", "generation_seconds_batch": 24.28177899005823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22709134221076965, "target_z": -0.24414062330486552, "ce": 5.998785495758057, "genuineness": 4.287685871124268, "identity": 0.677312970161438, "hypothesis": "De deur staat nog open. Ik inzit, het deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.3684210526315789, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c4171e419ad384ad8198481919b90b470dda82a1dbabb1b824d51a90b5681284.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "c43cac3790c87d270f1531498578646bd6d344e85f20e67419d103fed1611a7c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "79a2d51324f4a6d85d19073adf472541559372c29bc6a6670615fed560a41365", "generation_seconds_batch": 18.560083865071647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23741959035396576, "target_z": -0.2333984378632431, "ce": 6.205295085906982, "genuineness": 4.607763767242432, "identity": 0.5687879323959351, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c43cac3790c87d270f1531498578646bd6d344e85f20e67419d103fed1611a7c.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "28ab7d1420e44477813a3dc507c0a285eda7ea62c94e40e40b0a5a228ff27bbb", "generation_seconds_batch": 19.5456306389533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12944242358207703, "target_z": -0.34570313202270003, "ce": 6.133810997009277, "genuineness": 4.300237655639648, "identity": 0.7005845904350281, "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_Emotional_Numbness/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "c57dd8f4aaa0069f2ecaedf795d4d5ced713fd74e4c966df2a48c42827a67282", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f905b8ee2b9f324550e9cce17d8f539942cba3007174f87ea32f3b8e7ec1607d", "generation_seconds_batch": 22.86744919209741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7284809350967407, "target_z": 0.2773437475783793, "ce": 5.959072113037109, "genuineness": 4.595211505889893, "identity": 0.7634692192077637, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samenheen 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_Emotional_Numbness/c57dd8f4aaa0069f2ecaedf795d4d5ced713fd74e4c966df2a48c42827a67282.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "c60bafc390a7fa4fa3aae787971d905b37e6b21a1eb060482b4327662a87bf8a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "51884ed49afc16c4aa2720dbdc7af7618db9c276f02c74838952a643da7c4c03", "generation_seconds_batch": 25.50047402200289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24305318295955658, "target_z": -0.22753906116810863, "ce": 5.808161735534668, "genuineness": 4.7332844734191895, "identity": 0.7757730484008789, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c60bafc390a7fa4fa3aae787971d905b37e6b21a1eb060482b4327662a87bf8a.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "c6ebad667737933dbb2d75c8d832f2d56099c2a7ea2a4cc6fc248a9bf478efff", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "3beda9ab75bf86f26c188735639e2864f5b242e42f5fbee4c8d2c2da89522128", "generation_seconds_batch": 21.357351392973214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5425724387168884, "target_z": 0.08398437863243105, "ce": 5.808161735534668, "genuineness": 4.808597087860107, "identity": 0.6750780940055847, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "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_Emotional_Numbness/c6ebad667737933dbb2d75c8d832f2d56099c2a7ea2a4cc6fc248a9bf478efff.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "c6f55083a32dd58f1412d4fa6bd9650152205fb18de4e41eb933f0a99080dcaa", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c981642c1ae7334a598da05670effa4ac4d9ef22562d9921b3f173bec3463d6b", "generation_seconds_batch": 25.352902862941846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24680891633033752, "target_z": -0.2236328048718948, "ce": 6.070269584655762, "genuineness": 4.645420074462891, "identity": 0.7952080368995667, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c6f55083a32dd58f1412d4fa6bd9650152205fb18de4e41eb933f0a99080dcaa.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "c7deb2e59cef25fe680d79daef34137bf2c22740766663085611d53e594474e8", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "947447d04ed7de1b5fd5bb605b6a760fdbf2ddae943de105a51790ad063bc781", "generation_seconds_batch": 24.781772439950146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2411753237247467, "target_z": -0.22949218156702927, "ce": 6.133810997009277, "genuineness": 4.507347106933594, "identity": 0.24640125036239624, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c7deb2e59cef25fe680d79daef34137bf2c22740766663085611d53e594474e8.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "c7f33262700f33640eec159b6d52e634a67a14feb14d396b366e48b71a2bbc62", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b395ed0264b3335cf9093edf9b55fa636ed497dfdc30fa82299cfac7af95585f", "generation_seconds_batch": 19.019297926919535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25995397567749023, "target_z": -0.20996091558433266, "ce": 6.054384231567383, "genuineness": 4.344170093536377, "identity": 0.6519771814346313, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c7f33262700f33640eec159b6d52e634a67a14feb14d396b366e48b71a2bbc62.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": "c7fb4819475f894d4d08c1b8266eafec8fb4355a67f90a9fa43434a0a3cb0813", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The road turns left behind the bridge.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "11b6b96a9fe048927f693811c3d3d66ca4290069b5df5eb044aac921578361c5", "generation_seconds_batch": 27.485473950044252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4530218243598938, "target_z": -0.009155260587775157, "ce": 6.443574905395508, "genuineness": 4.557555198669434, "identity": 0.385955274105072, "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_Emotional_Numbness/c7fb4819475f894d4d08c1b8266eafec8fb4355a67f90a9fa43434a0a3cb0813.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "e6a4aed0b5d1f282d3f90e7c32c33fc2729786f9bbc221e2b58148229aca98a3", "generation_seconds_batch": 19.167552428902127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1162973940372467, "target_z": -0.3593749903135172, "ce": 6.260893821716309, "genuineness": 4.469690799713135, "identity": 0.4649352431297302, "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_Emotional_Numbness/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "c87a3986d96344a5a027a5406e6b6323a592ba4bbdb9fcadaff64f42e1b61c0c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d1349708961a915ee7f46b3e35056c8faaa8a076cdb6b69eafbebb5e0e2154fd", "generation_seconds_batch": 24.969033970031887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4181639552116394, "target_z": -0.0454101693872923, "ce": 6.022613525390625, "genuineness": 4.381826400756836, "identity": 0.744718074798584, "hypothesis": "Ik 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_Emotional_Numbness/c87a3986d96344a5a027a5406e6b6323a592ba4bbdb9fcadaff64f42e1b61c0c.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "2d62433a1986f0e36c074a124f3c0f817b1a1efb9a4b7a510c087afcdf57a809", "generation_seconds_batch": 18.299531226046383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09939661622047424, "target_z": -0.37695312039892065, "ce": 6.41180419921875, "genuineness": 4.243753433227539, "identity": 0.38920965790748596, "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_Emotional_Numbness/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "c89440a55728e105a25322405e484589c5b7603600c8cb0ebebdcf6d953b994f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2668725a80210473e31d0aa7c636af7cfcaba5adf8137fb98f5e60131218ee47", "generation_seconds_batch": 24.317944371025078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22709134221076965, "target_z": -0.24414062330486552, "ce": 6.205295085906982, "genuineness": 4.871357440948486, "identity": 0.3402167558670044, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c89440a55728e105a25322405e484589c5b7603600c8cb0ebebdcf6d953b994f.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "c8bdc0a4f7fc8d1582013dce9985ddcd244903bd5a9e9e9e81c037ada1e5167e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8395e3b9228fe68f0e7600f961e7ef04715757715050cfa3535f037b0da349a1", "generation_seconds_batch": 23.03477882198058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1801447570323944, "target_z": -0.2929687417664896, "ce": 6.125868320465088, "genuineness": 4.482243061065674, "identity": 0.781606912612915, "hypothesis": "Ik 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_Emotional_Numbness/c8bdc0a4f7fc8d1582013dce9985ddcd244903bd5a9e9e9e81c037ada1e5167e.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "c8fa5a419452cf96471ab164f27d3a0acd69d3c22e9905189c4b17700f96e0dc", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e22b7b30b8a28b4b70984bac403ce7fc93bb926c049e70bb3f75ce7d8b9d9ebc", "generation_seconds_batch": 17.058613940957002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20080125331878662, "target_z": -0.2714843708832448, "ce": 6.173524379730225, "genuineness": 4.7458367347717285, "identity": 0.6016971468925476, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/c8fa5a419452cf96471ab164f27d3a0acd69d3c22e9905189c4b17700f96e0dc.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "c98c38bd8e74148a363f4957ed6a8afc4a3c7bccf618f3b15bb0117b62b2a7e5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bff1de0fe2fa07afdae512d12a3e056b3f45c091ac26616b53ece9baa75fe3c5", "generation_seconds_batch": 18.74371704494115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5867022275924683, "target_z": 0.12988280874648792, "ce": 6.0146708488464355, "genuineness": 4.507347106933594, "identity": 0.4853886365890503, "hypothesis": "De deur 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_Emotional_Numbness/c98c38bd8e74148a363f4957ed6a8afc4a3c7bccf618f3b15bb0117b62b2a7e5.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "c9ee888d10e53b5f441ac3fdeedcfe0a8b5bb416b48e7b7c1c694fa98582c7c3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "becb748ca1a811d1348ef0149d6f12c8755eab9b113efd924ccc72a929a47686", "generation_seconds_batch": 25.057062993058935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7472596168518066, "target_z": 0.2968750445578209, "ce": 5.764476776123047, "genuineness": 4.419482707977295, "identity": 0.34991568326950073, "hypothesis": "De deur 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_Emotional_Numbness/c9ee888d10e53b5f441ac3fdeedcfe0a8b5bb416b48e7b7c1c694fa98582c7c3.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "caa3634962a035f8770a7e151ffda83906d17df214393519ff0675075b7be6b3", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3e91bc349deea5574f9e42f180899f3ecd5b9f76e3b6fbca1334194d585ee2b3", "generation_seconds_batch": 25.24216042109765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07874011993408203, "target_z": -0.3984374912821655, "ce": 6.23706579208374, "genuineness": 3.8169827461242676, "identity": 0.2807738780975342, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/caa3634962a035f8770a7e151ffda83906d17df214393519ff0675075b7be6b3.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "cad08d9b42ddccf48b53585b3c21a6b684bb44c5a69d7032d06dc4cc076c5186", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f51c8b4dd201b83230083305a3637643699a9a6c4009bdbbae376b0d870bb710", "generation_seconds_batch": 26.176872087060474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10503020882606506, "target_z": -0.37109374370378617, "ce": 6.173524379730225, "genuineness": 4.042920112609863, "identity": 0.17656747996807098, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/cad08d9b42ddccf48b53585b3c21a6b684bb44c5a69d7032d06dc4cc076c5186.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "cad0a6a9eeff4f7fc36adcb4028c17697ab9da115d1173a7ad46bd4e0eab7794", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d3451d45c5ba08dce80cff7003f264ab2f1dc82e3d0f84ef9b0af538301d63ce", "generation_seconds_batch": 19.18657450005412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18577834963798523, "target_z": -0.28710936507135515, "ce": 6.348263263702393, "genuineness": 4.444586753845215, "identity": 0.5300613641738892, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/cad0a6a9eeff4f7fc36adcb4028c17697ab9da115d1173a7ad46bd4e0eab7794.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "cb129616b2f266cf3f0d0042af71d7c1b631c02af6afa39e58b19d7a3e5945c0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4d3d812028ccfbbcef0c866be43046db6924aadf1e40620b45c53ba4a0dc61f0", "generation_seconds_batch": 25.061987460008822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6580610275268555, "target_z": 0.20410153888919816, "ce": 6.046441555023193, "genuineness": 4.570107460021973, "identity": 0.5178167819976807, "hypothesis": "Ik 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_Emotional_Numbness/cb129616b2f266cf3f0d0042af71d7c1b631c02af6afa39e58b19d7a3e5945c0.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "cb799ab3dac2ae31ebc5d154aa14103c9da2a27c17894903234d70e7b6863a10", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "15a1155e11bc03bc0844c1e2f2c0210dced4fae7066556b002f16a9c8b1f6a59", "generation_seconds_batch": 24.534473272040486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2918776273727417, "target_z": -0.17675782230756384, "ce": 6.205295085906982, "genuineness": 4.6705241203308105, "identity": 0.7283570766448975, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/cb799ab3dac2ae31ebc5d154aa14103c9da2a27c17894903234d70e7b6863a10.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "cbf637e4e74d99d24b318c9fb44cad4e44efbb98b98ada5c7d19703558168a3b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c7033b9d03e7285f597ce8984660a5d9c4c9fc0750c492eea3e2779fbc5e5131", "generation_seconds_batch": 24.864924479974434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17638900876045227, "target_z": -0.29687501356107593, "ce": 6.070269584655762, "genuineness": 4.607763767242432, "identity": 0.6327801942825317, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/cbf637e4e74d99d24b318c9fb44cad4e44efbb98b98ada5c7d19703558168a3b.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "cc322c443938b817c3b512a6c8c2812cfd710dbd8f61ab8f3dc423e8be2f6d45", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7b74e4a9ff0ccb1bbe612a062568b4fb5738bf04b82a55793d78c8045f28c2aa", "generation_seconds_batch": 26.623387007974088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8317634463310242, "target_z": 0.3847656329913483, "ce": 5.816103935241699, "genuineness": 4.758388519287109, "identity": 0.6791961193084717, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuando 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_Emotional_Numbness/cc322c443938b817c3b512a6c8c2812cfd710dbd8f61ab8f3dc423e8be2f6d45.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "cc9db35d82c73540ad3ade8c5dcadd185c347712a53bf96b4b10cce9606b5a20", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ce62d357d972147f6613fc37caab255870492415df8251b048296286d836f78a", "generation_seconds_batch": 23.524446388939396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23272493481636047, "target_z": -0.23828124660973102, "ce": 5.824047088623047, "genuineness": 4.545003414154053, "identity": 0.8005061149597168, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/cc9db35d82c73540ad3ade8c5dcadd185c347712a53bf96b4b10cce9606b5a20.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "ccfb22d9ebc838780b54f90ac7a52d37ed9c556f6ae587c7a9962f0eba6c7f4e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "88ea8ca640661f40d948b60cafaaacb6fa04d3526844a895e1f23d0821c29fdb", "generation_seconds_batch": 22.394712947076187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48412391543388367, "target_z": 0.02319334542041071, "ce": 5.764476776123047, "genuineness": 4.444586753845215, "identity": 0.5303178429603577, "hypothesis": "Ik 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_Emotional_Numbness/ccfb22d9ebc838780b54f90ac7a52d37ed9c556f6ae587c7a9962f0eba6c7f4e.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "cd53bb71e02a865c9570fe61b07dde218d6fd92bd3b97f6f3bc28324b701915b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c547e3a0eb3d9c80e5a58cd43566aa8d8c2797c42c9422f70869e38e1641e69e", "generation_seconds_batch": 23.81642697704956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2486867755651474, "target_z": -0.22167968447297412, "ce": 6.41180419921875, "genuineness": 4.632867813110352, "identity": 0.6281942129135132, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/cd53bb71e02a865c9570fe61b07dde218d6fd92bd3b97f6f3bc28324b701915b.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "cd80e7a9bd5e939669fbfaa2801cc4cc53eacb55dedd1a312d7c83880c906e72", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3a4a59b1f1da22359d4c21caa2b6a69fda518f10fb27c9fdf537097e35dc57f6", "generation_seconds_batch": 24.43625410401728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2026791274547577, "target_z": -0.26953123498595166, "ce": 6.046441555023193, "genuineness": 4.457139015197754, "identity": 0.32747718691825867, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/cd80e7a9bd5e939669fbfaa2801cc4cc53eacb55dedd1a312d7c83880c906e72.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": "cd82c8e22666b838db7cb8778a4e2118a542627422f2a3e880315f4a09e38e46", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The keys are on the kitchen table.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "758f8fdb76e42c97d5697ee1eedcde76254ef036778e4ff716922dc6e5ac8be3", "generation_seconds_batch": 19.019334623008035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15385466814041138, "target_z": -0.3203124893448689, "ce": 6.165581703186035, "genuineness": 4.419482707977295, "identity": 0.16948673129081726, "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_Emotional_Numbness/cd82c8e22666b838db7cb8778a4e2118a542627422f2a3e880315f4a09e38e46.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "cdfe663a317a69319fa7fc282afe49a60f51a4afb41cd5c71c7d5ae079fddef2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "dfd5694a84bcd49548f4e11142d550074029f24488baf2a6bdbcd46dc9166d04", "generation_seconds_batch": 26.40845945291221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17263329029083252, "target_z": -0.3007812543589173, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.5596415400505066, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/cdfe663a317a69319fa7fc282afe49a60f51a4afb41cd5c71c7d5ae079fddef2.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "ce2edc1d984edf61dca177ca21188dd0ec7ad996df91a563ce499709f999e8f7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f9fa96a458c486f1b554459d4289689fd4d1b9be6bb52417dfb1afe7759e2cce", "generation_seconds_batch": 23.77399856306147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1801447570323944, "target_z": -0.2929687417664896, "ce": 6.1020402908325195, "genuineness": 4.6203155517578125, "identity": 0.8221338987350464, "hypothesis": "La porte 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_Emotional_Numbness/ce2edc1d984edf61dca177ca21188dd0ec7ad996df91a563ce499709f999e8f7.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": "ce52940f3781fd16722f3ba944b4f8b2863db43f59d13e9dca8cec2390cedffd", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71344c250d5657765f7367951b37d796c95e1fa914e53fbb5e453e3c45410f5e", "generation_seconds_batch": 23.77727673703339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5369388461112976, "target_z": 0.07812500193729656, "ce": 6.086154937744141, "genuineness": 4.68307638168335, "identity": 0.647119402885437, "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_Emotional_Numbness/ce52940f3781fd16722f3ba944b4f8b2863db43f59d13e9dca8cec2390cedffd.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "ceca01b142caa73e6b7cf91ceab51f3007e47b7e296e3932d362cbcbdd4280d2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0cd3893dfc2c72db69439d3096099651e9ec4a4bdac6b76e6f41eb29bb9805fa", "generation_seconds_batch": 26.286469950922765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30032801628112793, "target_z": -0.1679687572648621, "ce": 5.9431867599487305, "genuineness": 4.444586753845215, "identity": 0.4632035791873932, "hypothesis": "The 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_Emotional_Numbness/ceca01b142caa73e6b7cf91ceab51f3007e47b7e296e3932d362cbcbdd4280d2.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "ced88bb5c9692b668a98924849949b4d6e5fc258e55c4ba7246df14b0bd660aa", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bacb642e8004a670bf8574363d40f7ac8ed0ab0d8bff4222a021f5680a7e9c41", "generation_seconds_batch": 19.45931131497491, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14446532726287842, "target_z": -0.3300781378345897, "ce": 6.3641486167907715, "genuineness": 4.444586753845215, "identity": 0.5974194407463074, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ced88bb5c9692b668a98924849949b4d6e5fc258e55c4ba7246df14b0bd660aa.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "cf28167ab57737a2b4207ae0af6dab1fc23bd60c3f97a972d2d3289a530eabcc", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "990f8f182c3cc89c56102be64e1a53dad49c44cd3c58daf7505c9bf7475fd7b1", "generation_seconds_batch": 24.32474495691713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14446532726287842, "target_z": -0.3300781378345897, "ce": 6.308549880981445, "genuineness": 4.607763767242432, "identity": 0.6223794221878052, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/cf28167ab57737a2b4207ae0af6dab1fc23bd60c3f97a972d2d3289a530eabcc.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "11e9a32cfce8249d498af8ea1e8b5300e07b62552df657f28826ac430ab9264b", "generation_seconds_batch": 20.019645459018648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10127449035644531, "target_z": -0.3749999845016275, "ce": 6.300607204437256, "genuineness": 4.419482707977295, "identity": 0.6865167617797852, "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_Emotional_Numbness/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "d05f7fee2cf5b0a3bd5c6c84a2325a5f6d6ef064b5d79ac4799a9b9f651d2f8c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "30baa43eba6e945a969371491fdb08ea0fff19f818c75f9200cd9f5e73dbd4e1", "generation_seconds_batch": 19.06429436604958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18577834963798523, "target_z": -0.28710936507135515, "ce": 6.205295085906982, "genuineness": 4.6705241203308105, "identity": 0.8785349130630493, "hypothesis": "La porte 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_Emotional_Numbness/d05f7fee2cf5b0a3bd5c6c84a2325a5f6d6ef064b5d79ac4799a9b9f651d2f8c.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "d0d78baa8c4a05e426c94d8c790ac80110afc57e592edc98847ec4be8d5ad809", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "38148fda929d3a0b256f4873ad60569dab4334e2648636c7e1930b17a50826f0", "generation_seconds_batch": 23.90075221308507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7190916538238525, "target_z": 0.26757816108214844, "ce": 5.395142555236816, "genuineness": 4.557555198669434, "identity": 0.8382924199104309, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/d0d78baa8c4a05e426c94d8c790ac80110afc57e592edc98847ec4be8d5ad809.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "d0e8dc84ba58b04a065eee7f59570e48a1b7875b91a1c6d851acbe55dfb44706", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6168cc79ad519c67ebe7ae44289be26f6b0756bd8c71bdab1faef80cd4225059", "generation_seconds_batch": 25.49756037502084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2646486163139343, "target_z": -0.20507812233621722, "ce": 6.125868320465088, "genuineness": 4.607763767242432, "identity": 0.7846283912658691, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/d0e8dc84ba58b04a065eee7f59570e48a1b7875b91a1c6d851acbe55dfb44706.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "d1096219cf741d20f7a3700b7fb7c9e04163e2bdff7a31db6e75dd4e984572d0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "18b8ab8bfe4f719800961c1417cdab0501b8a84b5d3a78c83da39eed6f359ff6", "generation_seconds_batch": 23.722369353985414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2890608310699463, "target_z": -0.17968751065513108, "ce": 5.7406487464904785, "genuineness": 4.21237325668335, "identity": 0.650496244430542, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d1096219cf741d20f7a3700b7fb7c9e04163e2bdff7a31db6e75dd4e984572d0.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "d10fc3f11946c435da3d8eb67958c4a6875631a7427c18120d1998bf0933e09e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f025ada7692b8141a04448000c56b3e13107b24d99b441bfca792ed88f509253", "generation_seconds_batch": 18.887540284078568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3256791830062866, "target_z": -0.1416015621367569, "ce": 5.903473377227783, "genuineness": 4.457139015197754, "identity": 0.5303473472595215, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d10fc3f11946c435da3d8eb67958c4a6875631a7427c18120d1998bf0933e09e.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "606639a98e8b731388356e709afc206526cce8e9b6fb86e5219fdaa01ba6a493", "generation_seconds_batch": 17.968193753040396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13319817185401917, "target_z": -0.34179686022811373, "ce": 6.372091293334961, "genuineness": 3.7918784618377686, "identity": 0.2994329631328583, "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_Emotional_Numbness/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "d1401570a7c057eac59fa615ea9b5213f8985c04fe81bb74f93a7b83dbb0cb2c", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c701ba0badec5acad95673c5349c1302a06551923335485e4c3049d785cb7b29", "generation_seconds_batch": 24.417032472090796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5108835101127625, "target_z": 0.05102541571904451, "ce": 5.649308204650879, "genuineness": 4.68307638168335, "identity": 0.6643192768096924, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d1401570a7c057eac59fa615ea9b5213f8985c04fe81bb74f93a7b83dbb0cb2c.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "d1558c2d23f01cff4b724a3bf0a87c9f5c0fe1340af1f4a030ac26ce9eaabc50", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "afe8de73c2d459dda899a2c240e5efbc1ed0312575fd04780c9e3dfd57d6012a", "generation_seconds_batch": 16.140830109012313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4666363298892975, "target_z": 0.005004889426551539, "ce": 5.4825119972229, "genuineness": 4.469690799713135, "identity": 0.6894946098327637, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d1558c2d23f01cff4b724a3bf0a87c9f5c0fe1340af1f4a030ac26ce9eaabc50.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "d169f8ff43a7733c8e8e46f04a505e5ab7e30f930d929c790f8af6b5e29c60a9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "78941e402d923e874983a5df359da9fce8c1a2382f23b01659098d4cce5f7e86", "generation_seconds_batch": 23.524230194976553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2580760717391968, "target_z": -0.2119140824783708, "ce": 5.831989288330078, "genuineness": 4.482243061065674, "identity": 0.7282373309135437, "hypothesis": "De deur 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_Emotional_Numbness/d169f8ff43a7733c8e8e46f04a505e5ab7e30f930d929c790f8af6b5e29c60a9.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "d21df8bd10274caadd30954ef2959c357d91308c859e76b3c75f4f5b6d77b929", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8db4ab5627b13407a0beac0cf6333e4bc930e99484ea373164f9546dc379fc11", "generation_seconds_batch": 24.26654276798945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15009891986846924, "target_z": -0.32421876113945525, "ce": 6.260893821716309, "genuineness": 4.457139015197754, "identity": 0.4508485198020935, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d21df8bd10274caadd30954ef2959c357d91308c859e76b3c75f4f5b6d77b929.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "7e6059c7b82cd89d8003d364c4c60eca4c832b97559732f0eaf2480ffd6230dc", "generation_seconds_batch": 19.947708321968094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0599614679813385, "target_z": -0.4179687572648621, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.7004098296165466, "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_Emotional_Numbness/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "d245e0fa0542ab764f384d74f2dd8db22b41173fe0f02f171c732d33b97c719e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "31723cf722cdb856f4d4f4daf53ecbe369fbde1f771dc349f29fd3df575da2e7", "generation_seconds_batch": 24.781772439950146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2177020162343979, "target_z": -0.25390625629621383, "ce": 5.95112943649292, "genuineness": 4.582659721374512, "identity": 0.14710265398025513, "hypothesis": "The 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_Emotional_Numbness/d245e0fa0542ab764f384d74f2dd8db22b41173fe0f02f171c732d33b97c719e.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": "d2693faf19f9fa5d5e7b41c948b49a3053ebff3a2a98fd05a32829bb08e3cc39", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "5c99ae9daadbe76fb04d80e6d4d05a443c09094d7f421c480764c3485241a0fb", "generation_seconds_batch": 18.731975344009697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9331680536270142, "target_z": 0.4902343515102792, "ce": 5.561938762664795, "genuineness": 4.607763767242432, "identity": 0.5785380005836487, "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_Emotional_Numbness/d2693faf19f9fa5d5e7b41c948b49a3053ebff3a2a98fd05a32829bb08e3cc39.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "d30142828dcd48b4081ac25b2474e78d1a70d2aa25371129bf64d7a7226dbd17", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f290dc8b8496e6f86a9ed4532c44185ba8be44967681599fc89e866c36362105", "generation_seconds_batch": 24.768963072099723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5214464664459229, "target_z": 0.06201171602567671, "ce": 5.601652145385742, "genuineness": 4.218649387359619, "identity": 0.6951570510864258, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuando 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_Emotional_Numbness/d30142828dcd48b4081ac25b2474e78d1a70d2aa25371129bf64d7a7226dbd17.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "d32890bd3dc901e8addffc34afdbdd4c4cb3620640ed63e3746305e72bba34eb", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9aa16c940a526ed7cb29a85757adab9cd9550a188b546c7ee3d98ea2366287b8", "generation_seconds_batch": 24.354019216028973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3632364571094513, "target_z": -0.10253906116810861, "ce": 5.847874641418457, "genuineness": 4.432034492492676, "identity": 0.7625292539596558, "hypothesis": "La porte 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_Emotional_Numbness/d32890bd3dc901e8addffc34afdbdd4c4cb3620640ed63e3746305e72bba34eb.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": "d3958372650d0ce6a7e85408bc90bec2b46e92c405af465dfb90316d81dc2bd2", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "73631701877a3e6f722c00cbb281f7afd5a04f6eca9bdd20dc9ac72d167f7443", "generation_seconds_batch": 26.114921011961997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4394072890281677, "target_z": -0.023315441598846822, "ce": 5.355429172515869, "genuineness": 4.6203155517578125, "identity": 0.721237063407898, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends les camps, tu partiras.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d3958372650d0ce6a7e85408bc90bec2b46e92c405af465dfb90316d81dc2bd2.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "d3b61ee8246a282bde681a8602d49d8bd4480663fab560a751c90f701229c238", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "26ea1a1c6338b1ef6f1e7d052aab2c062f7fa6c08404880955be238b3bcd576b", "generation_seconds_batch": 20.45745421096217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26277077198028564, "target_z": -0.20703122723676542, "ce": 5.911416053771973, "genuineness": 4.7458367347717285, "identity": 0.7855544090270996, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/d3b61ee8246a282bde681a8602d49d8bd4480663fab560a751c90f701229c238.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "bae04a9edc087dc92ee8cacc68c6ab9eaf36b89d1333ef651cd6ab70ef24efa0", "generation_seconds_batch": 15.852800325024873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07686224579811096, "target_z": -0.4003906271794586, "ce": 6.173524379730225, "genuineness": 4.293961524963379, "identity": 0.6488078832626343, "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_Emotional_Numbness/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.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": "d44804beb30ad26c07466e8bb1518a07d91590b4b358ba27948269c8f99bd84c", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5e855e043aecd24868af18404c88feec12b20f5573b84e06942111e87b6d8978", "generation_seconds_batch": 18.36375128303189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8111069202423096, "target_z": 0.3632812311113585, "ce": 5.824047088623047, "genuineness": 4.65797233581543, "identity": 0.7169383764266968, "hypothesis": "La carretera irá a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d44804beb30ad26c07466e8bb1518a07d91590b4b358ba27948269c8f99bd84c.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "d516221437a73d92c1a7cebc624ec62c6be50ba1372cf3ac960baeb894bef702", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cb60866fe7d55573600d071f053b7cc76332a6d601315b7f15a02a171fc09ea8", "generation_seconds_batch": 22.61510144593194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1388317346572876, "target_z": -0.3359375145297242, "ce": 6.149696350097656, "genuineness": 4.287685871124268, "identity": 0.22005043923854828, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d516221437a73d92c1a7cebc624ec62c6be50ba1372cf3ac960baeb894bef702.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "d51cab2432af2ff1e0e6fc8e313bb96a25f503d15a39e652be04c243ebf388bc", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "42457425931c976a434f228c4d43b30ffcce590f305a3a150f829290195088a0", "generation_seconds_batch": 24.303969447035342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17075541615486145, "target_z": -0.3027343902562104, "ce": 6.086154937744141, "genuineness": 4.632867813110352, "identity": 0.6892420053482056, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d51cab2432af2ff1e0e6fc8e313bb96a25f503d15a39e652be04c243ebf388bc.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": "d5cbe22c1dfea851f7756046707490f83f33970699728c73a61c2ae637591603", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f64813ff87b2330d0eae2e8c0538871ed443198d31608b4c0f16ad0ad6527d1", "generation_seconds_batch": 24.845724854967557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8674428462982178, "target_z": 0.42187499806270345, "ce": 5.673136234283447, "genuineness": 4.607763767242432, "identity": 0.7686845660209656, "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_Emotional_Numbness/d5cbe22c1dfea851f7756046707490f83f33970699728c73a61c2ae637591603.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "d5d3585b0006f0987234d4ce46679de1ab9bee2256b04984c423f13dcaee00f4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cbde335fd894addf29aff797fa1c5f8ec0479750ec477b25c97fecf5c309358c", "generation_seconds_batch": 19.00098270806484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4120609164237976, "target_z": -0.051757806809191356, "ce": 5.847874641418457, "genuineness": 4.883909225463867, "identity": 0.7781586050987244, "hypothesis": "La porte 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_Emotional_Numbness/d5d3585b0006f0987234d4ce46679de1ab9bee2256b04984c423f13dcaee00f4.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": "d5fb3f391ebdb865a3c6ec39c5947f2c504085f07c19f21309d9ba173fde0429", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Someone moved the little blue chair.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "132541c0d8e7d8f71599fb1368cc302c02aa334287452d9abe8d9c817c691dd3", "generation_seconds_batch": 28.149077885085717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3247402310371399, "target_z": -0.14257814558377596, "ce": 6.4912309646606445, "genuineness": 4.632867813110352, "identity": 0.32758232951164246, "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_Emotional_Numbness/d5fb3f391ebdb865a3c6ec39c5947f2c504085f07c19f21309d9ba173fde0429.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": "d663b92664f1672afc4c9c45950f10e427e5c0ac707c43b14c6795b276fde02d", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "5ab4466172e0b3207843627fe38fb83219f7dd5f45a9bddbdd75bcd195622fde", "generation_seconds_batch": 16.406469826004468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5867022275924683, "target_z": 0.12988280874648792, "ce": 5.855817794799805, "genuineness": 4.6956281661987305, "identity": 0.5807608962059021, "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_Emotional_Numbness/d663b92664f1672afc4c9c45950f10e427e5c0ac707c43b14c6795b276fde02d.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "d6748d8ae5e2c57660a440f42e9c207c663c9d339e1e59d950b8ab1083514d7d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f7677564b18333d996486173c15c285237b984acf4fed9809f5d2058c48e6f7", "generation_seconds_batch": 25.67088706290815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5721487998962402, "target_z": 0.11474610628188713, "ce": 5.903473377227783, "genuineness": 4.337893962860107, "identity": 0.6820463538169861, "hypothesis": "Ik 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_Emotional_Numbness/d6748d8ae5e2c57660a440f42e9c207c663c9d339e1e59d950b8ab1083514d7d.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "d71a0be7b57a713315247249591b8dfe32f7e6a90108f6756fb4215bf6c0e7d0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e260286a1b319e3bb7d9b2de7ebb0807c9fb9203c85462cb29520d28ef1d5d1b", "generation_seconds_batch": 23.551363318925723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2993890941143036, "target_z": -0.1689453097151362, "ce": 5.935244083404541, "genuineness": 4.65797233581543, "identity": 0.9043102860450745, "hypothesis": "La porte 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_Emotional_Numbness/d71a0be7b57a713315247249591b8dfe32f7e6a90108f6756fb4215bf6c0e7d0.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": "d81a541048e25c393c855129d1eb2e5d061f9865f95e276ed8d4c3bed26a1cea", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "487a410ba9c2493ff5bd2b0f8a0ab7190451372cdf58f4892be57d78627e9c70", "generation_seconds_batch": 24.88891760504339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8918550610542297, "target_z": 0.4472656097437896, "ce": 6.038498878479004, "genuineness": 4.770940780639648, "identity": 0.6193279027938843, "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_Emotional_Numbness/d81a541048e25c393c855129d1eb2e5d061f9865f95e276ed8d4c3bed26a1cea.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "d939744c3571cc90da7a1377c361b5976f1879f6e1f53a83e971379557c63614", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f7db0d06efc4667c07ec3221bdfe25e1974440347010c259c72c7fc466137821", "generation_seconds_batch": 22.217980609973893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32380133867263794, "target_z": -0.14355466703730507, "ce": 5.935244083404541, "genuineness": 4.494794845581055, "identity": 0.6628676056861877, "hypothesis": "De deur staan nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d939744c3571cc90da7a1377c361b5976f1879f6e1f53a83e971379557c63614.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "d961d65a7e119056e3768126348c61a01ec6bd0d6e8428e19bea92885b71f1fe", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "dad496872d6224bb0b3ab70c278150750ab46c1083eb7e4c7d252a44fce641ea", "generation_seconds_batch": 24.443554840050638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.525202214717865, "target_z": 0.06591798782026302, "ce": 5.689021587371826, "genuineness": 4.582659721374512, "identity": 0.5750879049301147, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d961d65a7e119056e3768126348c61a01ec6bd0d6e8428e19bea92885b71f1fe.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "d963b3a6bd64f89115b35beb3407f0f6453533396608dbba6473f606fe238e85", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2231311e6a343300f5dcb6b0929837389921ff78b5b449e92da65c838a8a4595", "generation_seconds_batch": 18.302908636978827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1519767940044403, "target_z": -0.32226562524216207, "ce": 6.252951145172119, "genuineness": 4.532451152801514, "identity": 0.4484630823135376, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d963b3a6bd64f89115b35beb3407f0f6453533396608dbba6473f606fe238e85.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "d975875d7c2ce3ce9e125f9a9fa9f059acd78c0b9982b5d2a671dfd7e5fb54fa", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97c3d978e7f76fbc7c08a64ace57fd09aed28b6f44cf863554e630bd5db2b79f", "generation_seconds_batch": 25.67088706290815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7397481203079224, "target_z": 0.2890625009686483, "ce": 6.0305562019348145, "genuineness": 4.532451152801514, "identity": 0.6501843333244324, "hypothesis": "Ik 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_Emotional_Numbness/d975875d7c2ce3ce9e125f9a9fa9f059acd78c0b9982b5d2a671dfd7e5fb54fa.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": "d992e95430dafbdd46447ed95b892dd4f8648ab1d1f397fe42791d32a0150e85", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The keys are on the kitchen table.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "233ae6604a1486903d7e8807fa5b560574beec3ce39722a0e9c3eb2747b4aa39", "generation_seconds_batch": 24.261023254017346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23460279405117035, "target_z": -0.23632812621081034, "ce": 6.332377910614014, "genuineness": 4.6705241203308105, "identity": 0.36407366394996643, "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_Emotional_Numbness/d992e95430dafbdd46447ed95b892dd4f8648ab1d1f397fe42791d32a0150e85.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "d994cdf0e48c38043905fbe75a48888757787fb8ad40cd204ac7515e2f13a2b1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "07b9aacd6350080b0faa929d871f13daf18496b2cb408a6428cbba2870b61f8b", "generation_seconds_batch": 23.1093726020772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14258748292922974, "target_z": -0.3320312427351379, "ce": 6.2767791748046875, "genuineness": 4.532451152801514, "identity": 0.6764630079269409, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/d994cdf0e48c38043905fbe75a48888757787fb8ad40cd204ac7515e2f13a2b1.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "d9b25d16dabd4be78452de63a1349f00339dbe7a6780260b2175241ca26a9408", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "03529915a49372b96231598c37579ca34e4a1e71068b0d61cfd100f220994126", "generation_seconds_batch": 23.58705886802636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8317634463310242, "target_z": 0.3847656329913483, "ce": 5.879645347595215, "genuineness": 4.632867813110352, "identity": 0.6738469004631042, "hypothesis": "De deur 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_Emotional_Numbness/d9b25d16dabd4be78452de63a1349f00339dbe7a6780260b2175241ca26a9408.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "d9bce2eb6528434e6fc63b876e9d74cc15573daeb42ea98ce9b5cb411f11f4dc", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "601b807eb658b3a6d3290201d1913e553ce0dd0ef294a7158f9118a272119dea", "generation_seconds_batch": 22.701952985022217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2233356088399887, "target_z": -0.24804687960107932, "ce": 6.173524379730225, "genuineness": 4.6705241203308105, "identity": 0.747317373752594, "hypothesis": "Ik 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_Emotional_Numbness/d9bce2eb6528434e6fc63b876e9d74cc15573daeb42ea98ce9b5cb411f11f4dc.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "dabb1c6d3d9f0b08ed7454a80fe485ea15d70687b71ded08f6ea7beaf8f7dfde", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7088aa50ec89f2b3475664eb84fd7f94d40bb4a7a14bb38420340d62e2b10353", "generation_seconds_batch": 25.689706429024227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5486754775047302, "target_z": 0.0903320160543301, "ce": 5.474569320678711, "genuineness": 4.432034492492676, "identity": 0.7444159984588623, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/dabb1c6d3d9f0b08ed7454a80fe485ea15d70687b71ded08f6ea7beaf8f7dfde.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 55, "seconds_generated": 4.4, "mp3_sha256": "954e91f66f32e1d249494dcef343b9cdaf4c52ee4d58fb20bfb00dbd7101c94c", "generation_seconds_batch": 18.305927093024366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07874011993408203, "target_z": -0.3984374912821655, "ce": 6.292664527893066, "genuineness": 4.281409740447998, "identity": 0.2734816074371338, "hypothesis": "Your message arrived after I had left. I read it twice.", "wer": 0.5217391304347826, "duration_error_s": 5.799999999999999, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "db2adf6332d62a3a234e9572205e03a46ad7c896dc6cee2c96ec91670a3a52a2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8673aeef139d09fe80f0740412a30b80afd14534f2843ed515fcd83e7cadce2e", "generation_seconds_batch": 25.756641801912338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3881181478500366, "target_z": -0.07666015776351294, "ce": 5.8875885009765625, "genuineness": 4.645420074462891, "identity": 0.4365393817424774, "hypothesis": "De deur 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_Emotional_Numbness/db2adf6332d62a3a234e9572205e03a46ad7c896dc6cee2c96ec91670a3a52a2.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "db6ac6ef03341a913d48a2302327234b25df7674b6fa34ffb3d313da05e965f0", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6b16959ba3ce1812fdb93971a576db6d229cb5f5e7b2eaef284774c077878808", "generation_seconds_batch": 25.03262082999572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1745111644268036, "target_z": -0.2988281184616241, "ce": 5.9431867599487305, "genuineness": 4.457139015197754, "identity": 0.6257373690605164, "hypothesis": "Ik 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_Emotional_Numbness/db6ac6ef03341a913d48a2302327234b25df7674b6fa34ffb3d313da05e965f0.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": "db8be07aa7c75c9e448350579eb77a00c8be2eb121b46c867b0f7f1c9faf4267", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The road turns left behind the bridge.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "f4783e7feeaa7af14b4d2399fd4369028a1a37bbb7d5f489d2613a2417a5b199", "generation_seconds_batch": 18.92086409800686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4317784905433655, "target_z": -0.031249988376220637, "ce": 5.95112943649292, "genuineness": 4.469690799713135, "identity": 0.3937321901321411, "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_Emotional_Numbness/db8be07aa7c75c9e448350579eb77a00c8be2eb121b46c867b0f7f1c9faf4267.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "db8de944cab6e3cfb8df87495a611a52df86bd77758440961b0003bcad57a76a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4c6512cb7b1c28bd2dbe966f4e5e5893ae2524cb975e7a0649d9a4d5550ad95f", "generation_seconds_batch": 19.540201906929724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2637096643447876, "target_z": -0.20605470578323629, "ce": 5.855817794799805, "genuineness": 4.394378662109375, "identity": 0.6385737657546997, "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": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/db8de944cab6e3cfb8df87495a611a52df86bd77758440961b0003bcad57a76a.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "dbd9815ccb6bfd7a943d97384b7cf398c001ed22321074ffa0a0dfc4be0232ec", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "186edf13608a3d8055d0103ddb3f9ff6c54bb0849c06d011e7655e0917fc567b", "generation_seconds_batch": 24.654590261052363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5094751119613647, "target_z": 0.04956057154526089, "ce": 5.998785495758057, "genuineness": 4.65797233581543, "identity": 0.5031902194023132, "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_Emotional_Numbness/dbd9815ccb6bfd7a943d97384b7cf398c001ed22321074ffa0a0dfc4be0232ec.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "dc1fcae68064299f7127a5aecd7ecedcdf0d14c2a5bdc44579b83312174df894", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a5f3e3c92795bff512e129d55dcc61d92f0f00e45722452b2ed5606a772fe6c8", "generation_seconds_batch": 19.631717980024405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42520594596862793, "target_z": -0.038085948518374185, "ce": 5.6413655281066895, "genuineness": 4.632867813110352, "identity": 0.6027572154998779, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/dc1fcae68064299f7127a5aecd7ecedcdf0d14c2a5bdc44579b83312174df894.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "dc22a6ffa9e87c65773ebe3d99992a6c660ffdac5a6b683eca7f3c3d8421e5c9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be12cc77426760c48f18c0a60df4e172805f9d21299ec2560b75e476bb31d8c5", "generation_seconds_batch": 26.242445894051343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1876561939716339, "target_z": -0.2851562601708069, "ce": 6.24500846862793, "genuineness": 4.582659721374512, "identity": 0.39561939239501953, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/dc22a6ffa9e87c65773ebe3d99992a6c660ffdac5a6b683eca7f3c3d8421e5c9.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "dc7ea426023696746995a7c7d874cf1fe9e6ffba53875fda46e8f646fdcb41d1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "be8246f0d035f3fd51bc98213c1e4b37daebaefcfe2458a1806d2ffc62b15936", "generation_seconds_batch": 23.77399856306147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16324397921562195, "target_z": -0.3105468718518931, "ce": 6.260893821716309, "genuineness": 4.507347106933594, "identity": 0.5276557803153992, "hypothesis": "La porte 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_Emotional_Numbness/dc7ea426023696746995a7c7d874cf1fe9e6ffba53875fda46e8f646fdcb41d1.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "dccffb6dc3ce799d85b3d0cc535a0012c49f3192fe1aac26e665ed52c2afc480", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0a46266af1801117c7eb7f3073fba5dbe4fca4ee00c7ab2f3a4c16325a2a1087", "generation_seconds_batch": 18.560083865071647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30126696825027466, "target_z": -0.16699217381784304, "ce": 6.300607204437256, "genuineness": 4.419482707977295, "identity": 0.5217303037643433, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/dccffb6dc3ce799d85b3d0cc535a0012c49f3192fe1aac26e665ed52c2afc480.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "dd29effebf117e43ccec57b21103977c67a9213d845bf7d349f0c4067f36f840", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cc1044d06cb8f5552290ef80b63c0d0610d3141d95679483bc1cbfc248e31dd1", "generation_seconds_batch": 22.957526177051477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05620574951171875, "target_z": -0.42187499806270345, "ce": 6.268836498260498, "genuineness": 4.519899368286133, "identity": 0.3411286473274231, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/dd29effebf117e43ccec57b21103977c67a9213d845bf7d349f0c4067f36f840.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "dd9002617736136e4e35a1da4ab7b84310ab845e336485603ddfd02c9a5f69d1", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2c92bbabc8b4776d5b07a60027af5b31658d06f5b4cc2aa268df30d9d8cf7d05", "generation_seconds_batch": 18.9154817040544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14070960879325867, "target_z": -0.3339843786324311, "ce": 6.054384231567383, "genuineness": 4.425758361816406, "identity": 0.6362508535385132, "hypothesis": "Ik 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_Emotional_Numbness/dd9002617736136e4e35a1da4ab7b84310ab845e336485603ddfd02c9a5f69d1.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "dd9092959cc6f288d778d295a21672f686bec5efb425de0d513ea4ab1cf5eef6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4b0d2830250b3d60a06f401c616e45dcc14be69728e3d6b663a2fc94aa84885", "generation_seconds_batch": 25.88034756097477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6082976460456848, "target_z": 0.15234373208000682, "ce": 5.657250881195068, "genuineness": 4.344170093536377, "identity": 0.35896816849708557, "hypothesis": "Ik heb het kleine toosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/dd9092959cc6f288d778d295a21672f686bec5efb425de0d513ea4ab1cf5eef6.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "dea040e06d21d8360776c3ef1c1454a0d7b37357312f9aaafd80d2ecd2d57809", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d1bec642f4067d53365810c75733e2cd780db1a58022e267cdc82815021db782", "generation_seconds_batch": 24.920484559959732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17263329029083252, "target_z": -0.3007812543589173, "ce": 6.0146708488464355, "genuineness": 4.582659721374512, "identity": 0.5251071453094482, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/dea040e06d21d8360776c3ef1c1454a0d7b37357312f9aaafd80d2ecd2d57809.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "ded65ef74b3e84d42471932dab82d56d916dee6342d96375eae04ad296dd6f2d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a69f5b0ed434c805156e22d8661e8cc65d9da3871c4066e3bd478ebc2be5ecce", "generation_seconds_batch": 25.65041534404736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30408376455307007, "target_z": -0.1640624854702758, "ce": 6.0146708488464355, "genuineness": 4.7458367347717285, "identity": 0.818600594997406, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/ded65ef74b3e84d42471932dab82d56d916dee6342d96375eae04ad296dd6f2d.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "df3475cd86a4bbdf5461d45c23940d91b9091a174c57b6a914374d272014468d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ae29e4eee8eb721b4a4ce84095f15e66ef0b29e294df055f60e5385c807162ea", "generation_seconds_batch": 25.087426787940785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32661813497543335, "target_z": -0.14062497868973783, "ce": 5.7684478759765625, "genuineness": 4.482243061065674, "identity": 0.5349595546722412, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/df3475cd86a4bbdf5461d45c23940d91b9091a174c57b6a914374d272014468d.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "e02ab10a0ce086f4b74f126a5d44153ddb5453df91df076a854d87f328e116c7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "99e59a5bff989966eb9447e143cb8b9b1c97febba848d9d6e8f41b25eb9904d1", "generation_seconds_batch": 20.45745421096217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0881294310092926, "target_z": -0.38867187378918966, "ce": 6.165581703186035, "genuineness": 4.419482707977295, "identity": 0.8040434718132019, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/e02ab10a0ce086f4b74f126a5d44153ddb5453df91df076a854d87f328e116c7.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "e06107f2bc6cf7021445d42ad9f1bfc9bec378c700cbce1ca60f71a38763aee5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a9beb079e537d87305596944fe7065c01cda003d10229fbd8c10f3f2d80eb4fa", "generation_seconds_batch": 21.677612161962315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1078094244003296, "target_z": 0.6718750290594484, "ce": 5.609594821929932, "genuineness": 4.68307638168335, "identity": 0.7250832319259644, "hypothesis": "la puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e06107f2bc6cf7021445d42ad9f1bfc9bec378c700cbce1ca60f71a38763aee5.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": "e0e1c09fe9ddab955acafdc4c58a7e4e84c350f0d2ec99c4d393a20a7fd4eca4", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Escribí el número en el sobre.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "2050bb5f63e8e437c829af3c63571e5f8d2af7fbb5fcb5ebb13c53d9f128ab69", "generation_seconds_batch": 16.9954869489884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1876561939716339, "target_z": -0.2851562601708069, "ce": 5.522225379943848, "genuineness": 4.8588056564331055, "identity": 0.7051262855529785, "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_Emotional_Numbness/e0e1c09fe9ddab955acafdc4c58a7e4e84c350f0d2ec99c4d393a20a7fd4eca4.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "e19ae29f17a1cee1c76ab6350cdd108e559ab832d805c38a2c4e4a658d2e6c64", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4a248e85956167639bc8a95e991909069957ecd7db2bedee2979819c2a40fb3a", "generation_seconds_batch": 25.299058718956076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8862215280532837, "target_z": 0.441406295042145, "ce": 5.784333229064941, "genuineness": 4.469690799713135, "identity": 0.6514663100242615, "hypothesis": "De deur 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_Emotional_Numbness/e19ae29f17a1cee1c76ab6350cdd108e559ab832d805c38a2c4e4a658d2e6c64.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "e252566443a6fef5c418044131971a16d8ddf2bafd62065c83fed00a4be4d8ad", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "716423752ee5943203f709ce349c4a073dec4b52913ad61bee2c7e6f96cf724b", "generation_seconds_batch": 23.805819335975684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08249583840370178, "target_z": -0.39453125048432414, "ce": 6.268836498260498, "genuineness": 4.174716949462891, "identity": 0.2548588812351227, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e252566443a6fef5c418044131971a16d8ddf2bafd62065c83fed00a4be4d8ad.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": "e2622b85b8b5fd912e53267d76356ee2e58d6e35c76a456e3ba97c2816a06174", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Someone moved the little blue chair.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "f747c133d2f29e90534ca32154852d8726818867457f48bd26a53fc8aea04f36", "generation_seconds_batch": 16.482030913000926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5237938165664673, "target_z": 0.0644531436464794, "ce": 6.38003396987915, "genuineness": 4.720732688903809, "identity": 0.23019906878471375, "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_Emotional_Numbness/e2622b85b8b5fd912e53267d76356ee2e58d6e35c76a456e3ba97c2816a06174.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": "e2f84a9e0f0494ab2c1f8c7a3366f9c515f3f7479ccb8081a296ddaa68b33d72", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "71c53026b720f7aea93201cef8e4102e422b89aef81b0d3c7dba96eca857ae52", "generation_seconds_batch": 25.046935116988607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6749618053436279, "target_z": 0.22167966897460165, "ce": 5.927301406860352, "genuineness": 4.758388519287109, "identity": 0.7217007279396057, "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_Emotional_Numbness/e2f84a9e0f0494ab2c1f8c7a3366f9c515f3f7479ccb8081a296ddaa68b33d72.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "e3b8d7d1a8829edd8943e019de1475e155b7d2581430b5f48289ec631500ae01", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0b279665328f62928b209d1c5f680c9a1804c5f4864f36f7b0b465edb6259c6e", "generation_seconds_batch": 18.09223597997334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12944242358207703, "target_z": -0.34570313202270003, "ce": 5.77639102935791, "genuineness": 4.833701133728027, "identity": 0.7196328043937683, "hypothesis": "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_Emotional_Numbness/e3b8d7d1a8829edd8943e019de1475e155b7d2581430b5f48289ec631500ae01.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "e3d11be22ab3f370ffa43e08883a91aa89c184af57b80de2243e23da7a0b1fec", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "711fddd159273f68376ac4a0350f17b352083bdc4f0071ae47cda6cc7df03f6a", "generation_seconds_batch": 20.450155840953812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1745111644268036, "target_z": -0.2988281184616241, "ce": 5.95112943649292, "genuineness": 4.344170093536377, "identity": 0.6073747873306274, "hypothesis": "La porte 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_Emotional_Numbness/e3d11be22ab3f370ffa43e08883a91aa89c184af57b80de2243e23da7a0b1fec.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "e457b856cb5c5ecb595efde4b8ce8699b888a550864534558176235d862c7789", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "67780e146645a11ae89c19008bc6c236cfbf71d181731158d4cd06ce79ecfbb7", "generation_seconds_batch": 16.853723019943573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1388317346572876, "target_z": -0.3359375145297242, "ce": 6.157639026641846, "genuineness": 4.005263805389404, "identity": 0.31392785906791687, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e457b856cb5c5ecb595efde4b8ce8699b888a550864534558176235d862c7789.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "e46bb90a65e12b463a36b5c0d93d1db3a1b067cd67b92da034410ff1e71c67d9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5b5096d097da47a4f88b132d067a7779d3436b8af7f5f6f8464af677bd4082a2", "generation_seconds_batch": 25.34207286394667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7866947054862976, "target_z": 0.3378906194302724, "ce": 5.210475444793701, "genuineness": 4.457139015197754, "identity": 0.7500042915344238, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e46bb90a65e12b463a36b5c0d93d1db3a1b067cd67b92da034410ff1e71c67d9.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "e4ee89df636a1e1da1170df8e7482a779e406ff75f5a7ecf6baf80009d0975aa", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3b3884d12ffc153e4fdc2c1e247c694dd4af24de2e716068d47eeffc95d700cc", "generation_seconds_batch": 18.376792559982277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4597117006778717, "target_z": -0.002197266260675434, "ce": 6.086154937744141, "genuineness": 4.557555198669434, "identity": 0.7177070379257202, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e4ee89df636a1e1da1170df8e7482a779e406ff75f5a7ecf6baf80009d0975aa.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "e527661d564320045c375f91d2d4b8bdd7419005078e8396cb0101f73c625ae4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "df6dbd58cd7471fac6449fd8ada096c19c61b3d1818afb84e6055a004ed843e1", "generation_seconds_batch": 25.95370765600819, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45982906222343445, "target_z": -0.0020752010789842935, "ce": 6.173524379730225, "genuineness": 4.833701133728027, "identity": 0.6589963436126709, "hypothesis": "La porte 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_Emotional_Numbness/e527661d564320045c375f91d2d4b8bdd7419005078e8396cb0101f73c625ae4.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "e583838dd6b0d07ad0f964ce8805686e76b8a54aeda2173597157522e498462e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d509adeba1a0f3d6bc38e358dfcc9c776d6cb40c5e4428de0c322342fd099785", "generation_seconds_batch": 24.47970455500763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16136610507965088, "target_z": -0.31250000774918624, "ce": 6.292664527893066, "genuineness": 4.507347106933594, "identity": 0.15547777712345123, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e583838dd6b0d07ad0f964ce8805686e76b8a54aeda2173597157522e498462e.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": "e6c2220339bc06017e1256647a58fa635b2c77229e73e077df4dbd92cd8020ed", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "021c0c9cb382363bf7a1c0276c39bc90f1eac7397a09fe5c9823f6d33499dc05", "generation_seconds_batch": 24.88891760504339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1303436756134033, "target_z": 0.6953124118530065, "ce": 5.903473377227783, "genuineness": 4.6956281661987305, "identity": 0.5322481393814087, "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_Emotional_Numbness/e6c2220339bc06017e1256647a58fa635b2c77229e73e077df4dbd92cd8020ed.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "49dfa23d2e9d5e26b02c1a66175f325a613cb0a91eb286497bc9cf8927e34605", "generation_seconds_batch": 18.299531226046383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10878592729568481, "target_z": -0.3671875029059448, "ce": 6.403861999511719, "genuineness": 4.406930446624756, "identity": 0.36962890625, "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_Emotional_Numbness/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "e70304e0b552da243089fc001db3e27ebdb21d17eb1c73b128d797c2c1c57a57", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "39f4f1e48466d9deca55ebc2c09930ba68d9b2ae81b29dfdad3779906abd5697", "generation_seconds_batch": 27.293133305036463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19328978657722473, "target_z": -0.27929688347567244, "ce": 6.213237762451172, "genuineness": 4.557555198669434, "identity": 0.6621238589286804, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e70304e0b552da243089fc001db3e27ebdb21d17eb1c73b128d797c2c1c57a57.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "e718446c01c2b7722e18f4e4d0c45a040fc5b913696a0690ce7fa9c826dc3814", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9dc938159552c6ff1b4d1c5bb0c96fdacb754049896ca7daa10f18fd0f963d68", "generation_seconds_batch": 25.216349124908447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22896920144557953, "target_z": -0.24218750290594485, "ce": 6.133810997009277, "genuineness": 4.7332844734191895, "identity": 0.729033350944519, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e718446c01c2b7722e18f4e4d0c45a040fc5b913696a0690ce7fa9c826dc3814.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": "e71e47c8087dc9c49e2d58a6c1ad3ad8ebf1b82e832084daf6acc381ea806fca", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "884aaf72bdb4b3e7064d48951828f5334ce8e61af6778ea1e59b8107743d3a38", "generation_seconds_batch": 23.041774076991715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7791832685470581, "target_z": 0.3300781378345897, "ce": 5.5817952156066895, "genuineness": 4.457139015197754, "identity": 0.29631978273391724, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houtdijk. Ik wacht aan de andere kant.", "wer": 0.14285714285714285, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e71e47c8087dc9c49e2d58a6c1ad3ad8ebf1b82e832084daf6acc381ea806fca.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "e769d543a43e6b5799ffa83ce1756f8220191c7b31e5e1257db8191a4df8574f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ddb6fa727494960240c01195257d5c9e4952544752d41e4500bb9f1870fa51aa", "generation_seconds_batch": 26.351399013074115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15385466814041138, "target_z": -0.3203124893448689, "ce": 6.221180438995361, "genuineness": 4.770940780639648, "identity": 0.5968430638313293, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e769d543a43e6b5799ffa83ce1756f8220191c7b31e5e1257db8191a4df8574f.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "e784f753900966a527f46be229c99da597c7527e03e75544dae41274da8b57fa", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "09299a380c65f4d27dbd6b70870f00e30249ccbf200b8a8d9718c5dc783c1ed6", "generation_seconds_batch": 24.303969447035342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5075972080230713, "target_z": 0.04760740465122277, "ce": 5.935244083404541, "genuineness": 4.7332844734191895, "identity": 0.6265460252761841, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e784f753900966a527f46be229c99da597c7527e03e75544dae41274da8b57fa.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "e7a68deb84980abb7ea14cf6f0e726a74cb0e9393301fb5933e0ccbc778784d8", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e68f0b7187c17d39c2dfd841adae2ef6b0846586a65e920404ac1630c12fce5", "generation_seconds_batch": 21.601044927956536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32661813497543335, "target_z": -0.14062497868973783, "ce": 5.831989288330078, "genuineness": 4.7458367347717285, "identity": 0.6759973168373108, "hypothesis": "La porte 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_Emotional_Numbness/e7a68deb84980abb7ea14cf6f0e726a74cb0e9393301fb5933e0ccbc778784d8.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "e83fd46cf3bdb8a64562529987025b7a647b044da71956987b4ebb6004842f33", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "32137cf9fd792b8fbe0839a777340e92ac53072f21ee058e50073e5837179770", "generation_seconds_batch": 23.5798362250207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39234334230422974, "target_z": -0.07226562524216207, "ce": 5.919358730316162, "genuineness": 4.319066047668457, "identity": 0.5530350208282471, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e83fd46cf3bdb8a64562529987025b7a647b044da71956987b4ebb6004842f33.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "e845f34d0275b2acae85cf98eabe2e8729791b54ee286afbe68c9bfac913eefc", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7c4da900c10604b1ebb35edcd25fff03ff875894de0dfecd952d6d8267cb946b", "generation_seconds_batch": 23.69255176198203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8674428462982178, "target_z": 0.42187499806270345, "ce": 5.792276382446289, "genuineness": 4.469690799713135, "identity": 0.22098444402217865, "hypothesis": "Ik 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_Emotional_Numbness/e845f34d0275b2acae85cf98eabe2e8729791b54ee286afbe68c9bfac913eefc.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "e85bd7ec0e3495f5c256c66acb710d7066f4437e3518822edf7692dbc291bbdc", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "56381bf7367034157de4f73cdb42edbadd928d1ab5097d6161b64bb40225232e", "generation_seconds_batch": 23.360577886924148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18953406810760498, "target_z": -0.2832031242735138, "ce": 6.0305562019348145, "genuineness": 4.595211505889893, "identity": 0.7252514362335205, "hypothesis": "La porte 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_Emotional_Numbness/e85bd7ec0e3495f5c256c66acb710d7066f4437e3518822edf7692dbc291bbdc.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "e8988e67f25eec6e548857100dc6ce3857ee948fb873b516b94193c73af716c7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "515dec47c5e285322d035859df3a544b69882b6fc8d51d4634e2cbc2cadfa4b3", "generation_seconds_batch": 25.88034756097477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7097023129463196, "target_z": 0.25781251259242766, "ce": 5.919358730316162, "genuineness": 4.432034492492676, "identity": 0.7041972279548645, "hypothesis": "Ik 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_Emotional_Numbness/e8988e67f25eec6e548857100dc6ce3857ee948fb873b516b94193c73af716c7.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "e8bb66563b7c727cc495643195f3aba96ebb191bec6401522e5a3c3ae1870948", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a247acfe54ca032655a484b553c6f508def9ca8755e97e69e8eef25138d0eb66", "generation_seconds_batch": 16.140830109012313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8223741054534912, "target_z": 0.3749999845016275, "ce": 5.355429172515869, "genuineness": 4.469690799713135, "identity": 0.6628125905990601, "hypothesis": "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_Emotional_Numbness/e8bb66563b7c727cc495643195f3aba96ebb191bec6401522e5a3c3ae1870948.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "e8d7b97eae9765bca5f3eeaf54f53e905dd5aa619cd4f4ff9cc2a1d74e51aaad", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5f62064d86d696518e3955512df41d3691ddc57b754a5a8797c8d5ea409092d2", "generation_seconds_batch": 25.547298580990173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3331906199455261, "target_z": -0.13378908054107422, "ce": 6.0305562019348145, "genuineness": 4.507347106933594, "identity": 0.3800855278968811, "hypothesis": "De deur 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_Emotional_Numbness/e8d7b97eae9765bca5f3eeaf54f53e905dd5aa619cd4f4ff9cc2a1d74e51aaad.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "e8e64979a0876366810b39b1b0021fee1e5112dd49d8de726268c181ad443534", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f1aaaf9d5f5db50a06819719189365ef8ff045cb5ccb178ed97c294ca54c4632", "generation_seconds_batch": 26.567143480991945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18390047550201416, "target_z": -0.2890625009686483, "ce": 5.871703147888184, "genuineness": 4.7332844734191895, "identity": 0.7846983671188354, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e8e64979a0876366810b39b1b0021fee1e5112dd49d8de726268c181ad443534.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "34358a25332c371cc48967d63b5640bb3e3e51a7e1da36cc0085df40f82eeb0a", "generation_seconds_batch": 20.019645459018648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07874011993408203, "target_z": -0.3984374912821655, "ce": 6.356205940246582, "genuineness": 4.6705241203308105, "identity": 0.3658224940299988, "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_Emotional_Numbness/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "e9dc853a55e4041c9be560ea79e54707f3c61191a7423bca50f4f9f1ee823a78", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e01f3a508ea6e62bae0cc34b489493443c6f29941d0b32356e95a356affec47b", "generation_seconds_batch": 23.805819335975684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10503020882606506, "target_z": -0.37109374370378617, "ce": 6.229123115539551, "genuineness": 4.15588903427124, "identity": 0.4425239861011505, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/e9dc853a55e4041c9be560ea79e54707f3c61191a7423bca50f4f9f1ee823a78.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": "ea29513d55f62a7450b60a0dd9399ab7374c177c64b9c3c9c498f48cdcb8e4fc", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93a806719c322c8029c4d668ceb6994aca6d2eace81db32c897a4e19d070d642", "generation_seconds_batch": 18.43436354806181, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9256566166877747, "target_z": 0.4824218699145965, "ce": 5.839932441711426, "genuineness": 4.7458367347717285, "identity": 0.7513006329536438, "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_Emotional_Numbness/ea29513d55f62a7450b60a0dd9399ab7374c177c64b9c3c9c498f48cdcb8e4fc.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "ead3a9247382f7c04f0d6affe834cc0547ecb609dc84c920236ce0c59811d627", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5b0dc29c87eb132fe9b8967d1e0ad6ebdfe0be077cf30ac4fe5c0e84d10aa3f5", "generation_seconds_batch": 24.739525887998752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5350610017776489, "target_z": 0.07617189703674837, "ce": 6.0146708488464355, "genuineness": 4.796044826507568, "identity": 0.8886100053787231, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/ead3a9247382f7c04f0d6affe834cc0547ecb609dc84c920236ce0c59811d627.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "eb3dd31b89dcd8574519cb4df7a930a8b6ae1feeeadc1b6a2c8d2bb2f027ee97", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "55255ec38402987ea10ec7652bc62ed361b6bb14b94b2bf691a5055075ef15e9", "generation_seconds_batch": 23.690810365020297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23460279405117035, "target_z": -0.23632812621081034, "ce": 6.109982967376709, "genuineness": 4.821148872375488, "identity": 0.7753008604049683, "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_Emotional_Numbness/eb3dd31b89dcd8574519cb4df7a930a8b6ae1feeeadc1b6a2c8d2bb2f027ee97.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "eb55934cffb7d007171c34825ac1e017779850e8e266064fbad2c3884fcc0309", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "dfb4065d18638669977f67e3fac207a562d50d6df63681424d10b9765ba2bc41", "generation_seconds_batch": 24.768963072099723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4937479794025421, "target_z": 0.03320312427351379, "ce": 5.80021858215332, "genuineness": 4.808597087860107, "identity": 0.7113209962844849, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/eb55934cffb7d007171c34825ac1e017779850e8e266064fbad2c3884fcc0309.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "eb87993d97ce57ab708932b4017f53eca975de0e4ab0e3cbe16b85ee2d0c31af", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "28e3409c5b5d6d0575acb472b941c4753af308c29f8bf5f719158eba8a90fe8f", "generation_seconds_batch": 20.00443698395975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.352438747882843, "target_z": -0.11376952283486806, "ce": 6.1020402908325195, "genuineness": 4.645420074462891, "identity": 0.6978970170021057, "hypothesis": "Ik 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_Emotional_Numbness/eb87993d97ce57ab708932b4017f53eca975de0e4ab0e3cbe16b85ee2d0c31af.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "ebe862991283a1080a3f14e5de8711abc5e0e9990b420265db57d15bfa5bd622", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "19976007e1b44aeda876bdde5e5be0a429d7375f38b361ddeac8bd6159776909", "generation_seconds_batch": 26.243028732948005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24680891633033752, "target_z": -0.2236328048718948, "ce": 6.316492557525635, "genuineness": 4.532451152801514, "identity": 0.46964696049690247, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ebe862991283a1080a3f14e5de8711abc5e0e9990b420265db57d15bfa5bd622.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "dca4946664262869caacbb29350067a17fa716a634fd30d3e5c0365248b551e1", "generation_seconds_batch": 19.989352807984687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41135671734809875, "target_z": -0.052490228896083166, "ce": 6.181467056274414, "genuineness": 4.545003414154053, "identity": 0.7503297328948975, "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_Emotional_Numbness/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "ebf4150ff5df338738b27a6ad4c4f12537a5e35ffe9be7701fb34335998081fe", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "882f0cb356bfc19a8a15d64e7b51af0683e7770bbb5642688b85b09c724c2eee", "generation_seconds_batch": 25.52321206103079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.914389431476593, "target_z": 0.47070311652432756, "ce": 5.506340026855469, "genuineness": 4.7332844734191895, "identity": 0.5931618809700012, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ebf4150ff5df338738b27a6ad4c4f12537a5e35ffe9be7701fb34335998081fe.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "ec79be687cc2fc138ad4975aef2fa32c14da6390c1bc49356c807460a17b5756", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1af98c0c61206a3c27a3da59f72c9f14d43dda7d024d7982743baf7bfc31bd6e", "generation_seconds_batch": 23.273611894925125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.289999783039093, "target_z": -0.17871092720811202, "ce": 6.157639026641846, "genuineness": 3.8546390533447266, "identity": 0.5088327527046204, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ec79be687cc2fc138ad4975aef2fa32c14da6390c1bc49356c807460a17b5756.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "ee038f5c900608944c333685f9c5e35fa29657818d04b914aaf7ca25d3367ae7", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "43c3957a858b338b96d05e4d361c68384dee2b6c66da48656e9bd75404bedc49", "generation_seconds_batch": 18.999958459986374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3613585829734802, "target_z": -0.10449219706540176, "ce": 5.847874641418457, "genuineness": 4.381826400756836, "identity": 0.7036699056625366, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ee038f5c900608944c333685f9c5e35fa29657818d04b914aaf7ca25d3367ae7.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "ee1c104e7d59b4782262cd9430a94e1230d62412c6a1b8538c5d7c649b386757", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d41a514d6e6f1cf3e92b911d470a34e7eafc2788f265af7aebefe212452e9433", "generation_seconds_batch": 22.92594422295224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6636946201324463, "target_z": 0.20996091558433266, "ce": 5.434855937957764, "genuineness": 4.482243061065674, "identity": 0.5424627661705017, "hypothesis": "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_Emotional_Numbness/ee1c104e7d59b4782262cd9430a94e1230d62412c6a1b8538c5d7c649b386757.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "eeafa1779696ff7bed9ae5377b37a8a19201cf96773df41bfd1431d0085685e6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a3d92d8998e767b72a7924730a516b768d90529447d7da0323116199144a1c33", "generation_seconds_batch": 19.00098270806484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4710962474346161, "target_z": 0.009643552311284687, "ce": 5.816103935241699, "genuineness": 4.6203155517578125, "identity": 0.7511740326881409, "hypothesis": "La porte 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_Emotional_Numbness/eeafa1779696ff7bed9ae5377b37a8a19201cf96773df41bfd1431d0085685e6.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "ef074bd5a87c3a864c43444ccda76b0637a527782cdd96c5743439ac8e0c47d4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c15f6b8102fcfb450ca21af4fd6ec669ff9d5ce16555ba871ecc2c9c80d04a6f", "generation_seconds_batch": 24.730744856991805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5120571255683899, "target_z": 0.05224606753595591, "ce": 5.982900142669678, "genuineness": 4.494794845581055, "identity": 0.5498466491699219, "hypothesis": "De deur 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_Emotional_Numbness/ef074bd5a87c3a864c43444ccda76b0637a527782cdd96c5743439ac8e0c47d4.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": "ef98e987bc0c230472e9fd8546d81e6c3986c449cd35fc6b65991db0cfdf2f0e", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Someone moved the little blue chair.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "42b70ff2ccbdff1a55a7aa42ff79e819d5c45d8bf474d5bd848ca31eabd0d7d5", "generation_seconds_batch": 16.482030913000926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23741959035396576, "target_z": -0.2333984378632431, "ce": 6.062326908111572, "genuineness": 4.570107460021973, "identity": 0.35369449853897095, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunchtime.", "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_Emotional_Numbness/ef98e987bc0c230472e9fd8546d81e6c3986c449cd35fc6b65991db0cfdf2f0e.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "efe0adfbf15fcf3be26b94d1114696ce2043f8c4e8a840df349b044ea283cf09", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e5cc7e789c26704da4972a510a029aa523e9ba280d6c1a2359d892caa66f702", "generation_seconds_batch": 26.567143480991945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22709134221076965, "target_z": -0.24414062330486552, "ce": 6.213237762451172, "genuineness": 4.808597087860107, "identity": 0.6613866090774536, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/efe0adfbf15fcf3be26b94d1114696ce2043f8c4e8a840df349b044ea283cf09.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "effe1fa87d51a7f444fb46154695f293665100abec3cd20df8b14d495866e342", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8bdcd89fd3d989f4659c64869b269d053913c90f9cc01dc1b92db8126f84750d", "generation_seconds_batch": 18.51876401808113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6289541721343994, "target_z": 0.1738281339599966, "ce": 5.315715789794922, "genuineness": 4.645420074462891, "identity": 0.7114972472190857, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/effe1fa87d51a7f444fb46154695f293665100abec3cd20df8b14d495866e342.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "f0dd1b8b4512251c4145bf5a74d5b0f5aec1a81c58196c126cb4c916e476575b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "793b9d0b800e49cb1180624ad37c9b29d7a816bec4bfe36c6006e674bb7df497", "generation_seconds_batch": 23.77990686800331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09376302361488342, "target_z": -0.3828124970940552, "ce": 6.133810997009277, "genuineness": 4.432034492492676, "identity": 0.4994175434112549, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f0dd1b8b4512251c4145bf5a74d5b0f5aec1a81c58196c126cb4c916e476575b.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "f0e4b987191789f784384799bc11906cd574f1a9344a49868f7678a9f6cb7d4e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cea59d1e2c0779dacba21cc5718a4ee4f5bf08db4bd1614641f58dcca68676b6", "generation_seconds_batch": 20.289659190922976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8599313497543335, "target_z": 0.41406245447353085, "ce": 5.657250881195068, "genuineness": 4.381826400756836, "identity": 0.35034114122390747, "hypothesis": "De deur 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_Emotional_Numbness/f0e4b987191789f784384799bc11906cd574f1a9344a49868f7678a9f6cb7d4e.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": "f186e86f0bc40742ba38e95865b42c3922dd53d0c13b80cbb73dc1497605345c", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "1a2b83401a04698a82bd6ce2a2e0a5ace26dafc34cfa5d07083a83292d7dfb57", "generation_seconds_batch": 17.451551003032364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4951563775539398, "target_z": 0.034667968447297415, "ce": 5.557967185974121, "genuineness": 4.796044826507568, "identity": 0.617207407951355, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir cuit près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.041666666666666664, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f186e86f0bc40742ba38e95865b42c3922dd53d0c13b80cbb73dc1497605345c.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "f1bc747d4baab991956ab439d20bfc21957650234d9958b40908c1e19f9f5e67", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b2f9cea35149602997c97e6c50ddf450e43f42cba330c2457d7e153464b45f2", "generation_seconds_batch": 18.354109765030444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19892337918281555, "target_z": -0.27343750678053796, "ce": 6.197352409362793, "genuineness": 4.469690799713135, "identity": 0.3671145439147949, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f1bc747d4baab991956ab439d20bfc21957650234d9958b40908c1e19f9f5e67.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "8e20540f2a0a75c98a9b8a3914288a38195eee6523b6cf291494c924c1bcefc3", "generation_seconds_batch": 18.422360655036755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10127449035644531, "target_z": -0.3749999845016275, "ce": 6.332377910614014, "genuineness": 4.482243061065674, "identity": 0.6432531476020813, "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_Emotional_Numbness/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.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": "f21bcc9115f5443550667ca03874474ea6c306a9a0a424cbf8aa8cffe34a7250", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "26e86ee82af6d50a7a555cfce12f5b88bc1d0eff26fa2326a2cc51c174c80b17", "generation_seconds_batch": 22.392635217984207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8937329053878784, "target_z": 0.44921871464433777, "ce": 5.784333229064941, "genuineness": 4.7834930419921875, "identity": 0.7643102407455444, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f21bcc9115f5443550667ca03874474ea6c306a9a0a424cbf8aa8cffe34a7250.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "f24ddecb74d6c15454c5f9072b1a5a12a5f5afe7dc0423ca5b1c0e3a0ab2ae62", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7486611bbb955e3d5e6ad0ef6a50a9180569a3cbf5b603d3cc17bc27196b661d", "generation_seconds_batch": 26.96549383806996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22709134221076965, "target_z": -0.24414062330486552, "ce": 6.252951145172119, "genuineness": 4.607763767242432, "identity": 0.30485913157463074, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f24ddecb74d6c15454c5f9072b1a5a12a5f5afe7dc0423ca5b1c0e3a0ab2ae62.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "f261b5ca6136a6f9bdef4c59a09a4b52a163163cdda3be2bf09d0632b9ed3083", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7d5e57d56cbac0e90d1c524f49c2731f0eefe727e1e9b1fe56500049066c7a5c", "generation_seconds_batch": 23.877591513912193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5005552172660828, "target_z": 0.04028318378230465, "ce": 5.871703147888184, "genuineness": 4.394378662109375, "identity": 0.6099390387535095, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f261b5ca6136a6f9bdef4c59a09a4b52a163163cdda3be2bf09d0632b9ed3083.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "f3587226e92b9809ea31626258318f2031532af35e009cd98d2f538bd69036b5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b13ff61f937c1badb4808680a36a99ce7dc8c9fb8d8b652c672536d5ccdc27c0", "generation_seconds_batch": 25.39770676800981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06747293472290039, "target_z": -0.41015624467243444, "ce": 6.316492557525635, "genuineness": 4.570107460021973, "identity": 0.3109057545661926, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f3587226e92b9809ea31626258318f2031532af35e009cd98d2f538bd69036b5.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "f39081a2dcfd6e6dddcece681b036c7cdd2a8d00c6b7b4425ada9ca8b5610d68", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f561707935382570e30fd7567cbe5f54074810e0c3c766faed00d0e1672104c9", "generation_seconds_batch": 17.003160982974805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04869428277015686, "target_z": -0.4296875106551311, "ce": 6.24500846862793, "genuineness": 4.65797233581543, "identity": 0.30353260040283203, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f39081a2dcfd6e6dddcece681b036c7cdd2a8d00c6b7b4425ada9ca8b5610d68.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "f3d57187d94820badad0ab9d01d3a47c59d91bd2c487edb39f883c917456a220", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6455014f21101547e2ea8c1654caed6916a05207300164c0b90d4d0d99fda5c5", "generation_seconds_batch": 23.57447907293681, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5247327089309692, "target_z": 0.06542966510000851, "ce": 5.911416053771973, "genuineness": 4.406930446624756, "identity": 0.7651931047439575, "hypothesis": "De deur 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_Emotional_Numbness/f3d57187d94820badad0ab9d01d3a47c59d91bd2c487edb39f883c917456a220.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": "f448935a2892dbf6ca975395c3c0f5c7d7a2a0cbeac0117bb9090c5ea0ea83c5", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7e01246db5aad9ea3b0a453234f3707dc6bbc6ede6ede3ecffca67e78fb5c383", "generation_seconds_batch": 24.422542501008138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6223816275596619, "target_z": 0.16699217381784304, "ce": 5.665193557739258, "genuineness": 5.021982192993164, "identity": 0.6364091634750366, "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_Emotional_Numbness/f448935a2892dbf6ca975395c3c0f5c7d7a2a0cbeac0117bb9090c5ea0ea83c5.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "f49c8319006509b10cd87bd6e867bd01bc5f58e38bc5ea5c9aab58863ba923e2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f5f09a65725e4888063f5be737534e0735475206bc8202e5b011c8ed521e4e9f", "generation_seconds_batch": 25.39770676800981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06747293472290039, "target_z": -0.41015624467243444, "ce": 6.443574905395508, "genuineness": 4.444586753845215, "identity": 0.3706911504268646, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f49c8319006509b10cd87bd6e867bd01bc5f58e38bc5ea5c9aab58863ba923e2.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": "f4fee89e5978ca1d869826c64916a0fcf5b8a31cef3c97c78c92d6d7dcaa4a7c", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Your message arrived after I had left.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "88198cef1ab9f34bdbcf8f8f2e322018994215a1193547ecebf941a8958baaaa", "generation_seconds_batch": 19.386697283014655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6805953979492188, "target_z": 0.22753904566973612, "ce": 6.070269584655762, "genuineness": 4.6956281661987305, "identity": 0.1271359622478485, "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_Emotional_Numbness/f4fee89e5978ca1d869826c64916a0fcf5b8a31cef3c97c78c92d6d7dcaa4a7c.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "f56c03b6a0d802bdcfa5e3ff83e77674f8bf7c49481ed19316dfa611ee23e856", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5fb3688bf2c8ab57ca69fdb775bcd94b4ce851d05c878d21cca0c608143ab300", "generation_seconds_batch": 17.10325859102886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23648065328598022, "target_z": -0.2343750058118897, "ce": 5.974957466125488, "genuineness": 4.369274139404297, "identity": 0.7349838018417358, "hypothesis": "La porte 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_Emotional_Numbness/f56c03b6a0d802bdcfa5e3ff83e77674f8bf7c49481ed19316dfa611ee23e856.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "f5880f03285ecfb9ea24913af4dfb62d6f99703b7ea32f43361a20fc87c93c69", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8fd89fd962a52d3104458fa63734999587392a12f46152b30b3bdf6f5172e3a3", "generation_seconds_batch": 21.828531629987992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3853013515472412, "target_z": -0.07958984611108018, "ce": 5.80021858215332, "genuineness": 4.65797233581543, "identity": 0.5760449767112732, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f5880f03285ecfb9ea24913af4dfb62d6f99703b7ea32f43361a20fc87c93c69.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": "f606b9fdbb778c270489b2ed6be7f6a6ef06cb9ad9401d6c5d4bc588a8981732", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b585c7d33e0a32758180f29eb2efd054c1c0886e1aca9d12546b48561f2ecea9", "generation_seconds_batch": 18.629826614051126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8223741054534912, "target_z": 0.3749999845016275, "ce": 5.974957466125488, "genuineness": 4.65797233581543, "identity": 0.5763042569160461, "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_Emotional_Numbness/f606b9fdbb778c270489b2ed6be7f6a6ef06cb9ad9401d6c5d4bc588a8981732.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "f68028e9221511986c6190c461d07ad47beefba623d1dd8c404b31fcc733b483", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ac0ba7aa379ae864af2ccafc09b0f19846b8f585d70aacc206a24f5c705f08e4", "generation_seconds_batch": 25.547298580990173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2505646347999573, "target_z": -0.21972656407405344, "ce": 5.990842819213867, "genuineness": 4.507347106933594, "identity": 0.7281737327575684, "hypothesis": "De deur 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_Emotional_Numbness/f68028e9221511986c6190c461d07ad47beefba623d1dd8c404b31fcc733b483.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "f6ff6c0241f6e253ea51c81555b1739b4a59f3779b0dd8868eea90ee1e190b0e", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "13b5f1d1cea6b1fd8cb0f44c2d2b37bb237dbeefc2460bdc98e98694af034cc1", "generation_seconds_batch": 25.65599920495879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09376302361488342, "target_z": -0.3828124970940552, "ce": 6.316492557525635, "genuineness": 4.457139015197754, "identity": 0.2418099045753479, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f6ff6c0241f6e253ea51c81555b1739b4a59f3779b0dd8868eea90ee1e190b0e.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "f75342bd972dd5989af11c03066b8e3cb685f7a5cda909c11b0a6802c66ae5e8", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1fda1db956b40aae4cf5048255b764e0f53787c13245803f34c9fd0c36099be0", "generation_seconds_batch": 18.24210263893474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.874954342842102, "target_z": 0.42968754165187606, "ce": 5.847874641418457, "genuineness": 4.6705241203308105, "identity": 0.7705308794975281, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/f75342bd972dd5989af11c03066b8e3cb685f7a5cda909c11b0a6802c66ae5e8.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "f79811d6971132dd2d5403b9121660a9805a69de005b26953fe67f09c0171bfe", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b021c5e4a9847ce6d7ac0ff033f1b3b08f4bd556f68c950984d31d24969eb6de", "generation_seconds_batch": 24.833278203033842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19328978657722473, "target_z": -0.27929688347567244, "ce": 6.1894097328186035, "genuineness": 4.582659721374512, "identity": 0.14891991019248962, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f79811d6971132dd2d5403b9121660a9805a69de005b26953fe67f09c0171bfe.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": "7bef4b76495b74f6a49f638dd767eee6c4224fcc07b0f90b5bdd429c1a175a81", "generation_seconds_batch": 18.885165581014007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08249583840370178, "target_z": -0.39453125048432414, "ce": 6.268836498260498, "genuineness": 4.545003414154053, "identity": 0.6893916130065918, "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_Emotional_Numbness/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "f7a87d110c01096bb53edc2e971ae20fde4f7f768a66742651cea795c0c81916", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4a909eb518619d2399f336a853b4fcf11515dfc3b888113e5091b809cc13662f", "generation_seconds_batch": 25.458198643988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6345877647399902, "target_z": 0.17968751065513108, "ce": 5.609594821929932, "genuineness": 4.7332844734191895, "identity": 0.729312002658844, "hypothesis": "La porte 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_Emotional_Numbness/f7a87d110c01096bb53edc2e971ae20fde4f7f768a66742651cea795c0c81916.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "f810980b603f64f1a867473039f1b4f0b9bd94410d4ebfac71409eda06e5d679", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f6c1d8bccdfc84e559bb348c44e7cf3fa1152c60005637218bf59032e814db4c", "generation_seconds_batch": 18.9154817040544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21206843852996826, "target_z": -0.25976561749297583, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.7767922878265381, "hypothesis": "Ik 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_Emotional_Numbness/f810980b603f64f1a867473039f1b4f0b9bd94410d4ebfac71409eda06e5d679.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "f86b87cde2fc3ebf7df9bc4c1e0dc16b092bd34b470e33c4b0fa87ea324faf6a", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "4369380c871bd734058100b6d32b095b725754bcc5407953c3a1efc3a01f2d14", "generation_seconds_batch": 26.325081994989887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7604045867919922, "target_z": 0.3105468408551481, "ce": 5.434855937957764, "genuineness": 4.532451152801514, "identity": 0.6384658813476562, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f86b87cde2fc3ebf7df9bc4c1e0dc16b092bd34b470e33c4b0fa87ea324faf6a.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_Emotional_Numbness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7d0349c5350ba1537cb050a838ca37e559c92b84fa7b336cae828be1583914b", "generation_seconds_batch": 18.838446403038688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10127449035644531, "target_z": -0.3749999845016275, "ce": 6.395919322967529, "genuineness": 4.406930446624756, "identity": 0.5967910289764404, "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_Emotional_Numbness/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "f8754762c3a5d61d67e8a952e3265cd1ecbba1d702fb5cde8f828419d241b26f", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d0288e335adca63b2016c0eebd1627e57a494c58f3adbb77cf4aa767f4af873e", "generation_seconds_batch": 24.64245597901754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38483190536499023, "target_z": -0.08007810683784475, "ce": 5.80021858215332, "genuineness": 4.758388519287109, "identity": 0.8242685794830322, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/f8754762c3a5d61d67e8a952e3265cd1ecbba1d702fb5cde8f828419d241b26f.mp3" }, { "id": "emo_Emotional_Numbness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-1", "key": "f8863093a7eebc00b7b79dee9900b0883eca76c9f2e5d33945f761faa72e186d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "90ab5d848d7d011255f788e6ef5ab6dcc3535bf6c5d36b6c2f83ed3daf8382f0", "generation_seconds_batch": 23.44354350399226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8073512315750122, "target_z": 0.35937502131026217, "ce": 6.054384231567383, "genuineness": 4.6705241203308105, "identity": 0.6454476118087769, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f8863093a7eebc00b7b79dee9900b0883eca76c9f2e5d33945f761faa72e186d.mp3" }, { "id": "emo_Emotional_Numbness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-1", "key": "f8924f13c800ebc800d180de432e90277d685b472f2fbcac87623a78fffd48d6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d353bb82db93b2ec1442e06240999b29b8100918ccbb5357d07ee1793db3a932", "generation_seconds_batch": 18.577911864966154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35619446635246277, "target_z": -0.10986328203702672, "ce": 6.0305562019348145, "genuineness": 4.68307638168335, "identity": 0.7487923502922058, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/f8924f13c800ebc800d180de432e90277d685b472f2fbcac87623a78fffd48d6.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "f918164a5063608cb133fe3323094160420d4e4766147b3fb7cd4306f8f2533d", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7368a2395ca04698e64f541b49524703ee26c1d04515281a6f01f2033cea173e", "generation_seconds_batch": 26.413259892025962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12568670511245728, "target_z": -0.3496093728205414, "ce": 6.316492557525635, "genuineness": 4.68307638168335, "identity": 0.4222199320793152, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/f918164a5063608cb133fe3323094160420d4e4766147b3fb7cd4306f8f2533d.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "f91e00db8e21d017e0d99852db38166be0a2afbc81cb909ccd83506913bf7768", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "80d9eb6cccfb42739ecf4398eafb6d67062585ff1b8327769a309c52ecd12509", "generation_seconds_batch": 17.258823154959828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1801447570323944, "target_z": -0.2929687417664896, "ce": 6.086154937744141, "genuineness": 4.15588903427124, "identity": 0.3091428279876709, "hypothesis": "The 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_Emotional_Numbness/f91e00db8e21d017e0d99852db38166be0a2afbc81cb909ccd83506913bf7768.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": "f9a71a903819d885f6cb3ae8ac46ecd75b65d9ce1e0b4e35e9cf9323ce6c25e6", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "9377dbdd1c5422dd459a09e8eead85bdaa7e2f3168de1a817755be3f8f0a0461", "generation_seconds_batch": 18.731975344009697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.013916254043579, "target_z": 0.5742187921362002, "ce": 5.871703147888184, "genuineness": 4.7081804275512695, "identity": 0.763515830039978, "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_Emotional_Numbness/f9a71a903819d885f6cb3ae8ac46ecd75b65d9ce1e0b4e35e9cf9323ce6c25e6.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": "fa694722051afe5d2c06e31643b121baec8de19794bb9807ffe0ae8c8fc9e051", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Escribí el número en el sobre.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "63465c6a3e2971f5543e3124c29642ecc286b9867a7f55c70597d7f593a9302c", "generation_seconds_batch": 22.009171106037684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6214426755905151, "target_z": 0.16601559037082397, "ce": 5.577824115753174, "genuineness": 4.7081804275512695, "identity": 0.708538293838501, "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_Emotional_Numbness/fa694722051afe5d2c06e31643b121baec8de19794bb9807ffe0ae8c8fc9e051.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "fa9e03950fd39b27255b57fc5c47223856b7a467ee23e28266af7623ba03d19b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "5f8ac89b8de7a79d369a3566d969b94fa77d7a8e8377159b17bc005eef284836", "generation_seconds_batch": 24.75933765002992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7472596168518066, "target_z": 0.2968750445578209, "ce": 5.732706069946289, "genuineness": 4.7834930419921875, "identity": 0.678528904914856, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/fa9e03950fd39b27255b57fc5c47223856b7a467ee23e28266af7623ba03d19b.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "fae4c970b92b84c0aa0307a1029cfa505ee43d3f6d5b4f35ee93cf6d1f7b33c5", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7da76cb8cb00a07c798ca57c6557ca2dd85eb96d6e4ab39d4668ab8a9fb08632", "generation_seconds_batch": 18.65611454891041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5820075869560242, "target_z": 0.12500001549837247, "ce": 6.09409761428833, "genuineness": 4.432034492492676, "identity": 0.7699036598205566, "hypothesis": "Ik 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_Emotional_Numbness/fae4c970b92b84c0aa0307a1029cfa505ee43d3f6d5b4f35ee93cf6d1f7b33c5.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "faee48b6f81b8716d41cea57561b03eb924afbbcb5fe5aa2959cdccb66407455", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0b41fef5e34b8c57bab6f669e174419277dd6f409276216b1cab8e13c03bcd61", "generation_seconds_batch": 22.92594422295224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5571258664131165, "target_z": 0.09912108109703184, "ce": 5.649308204650879, "genuineness": 4.6956281661987305, "identity": 0.6960873603820801, "hypothesis": "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_Emotional_Numbness/faee48b6f81b8716d41cea57561b03eb924afbbcb5fe5aa2959cdccb66407455.mp3" }, { "id": "emo_Emotional_Numbness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-1", "key": "faef6cf5385fc5f74230b9de82e1893c3d1ca6df5a8e744b8c60a4539edb7af2", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I found the little box.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] It was beside the old window.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f31134d50050ea4891bbe00c3fe3777220aa200bb0a9dcdb2a4bc6be50c7d731", "generation_seconds_batch": 26.418593921000138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06183934211730957, "target_z": -0.4160156213675689, "ce": 6.38003396987915, "genuineness": 4.632867813110352, "identity": 0.39784178137779236, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/faef6cf5385fc5f74230b9de82e1893c3d1ca6df5a8e744b8c60a4539edb7af2.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "fb12a4bd417176a5c170aa0eecf2b803352b4f1a1a381f3ff05ff253200639c1", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "58103be23847e781664ad9cedd4f9615a3063734ee99f31807414fd040605eb3", "generation_seconds_batch": 25.55564652895555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 5.736677646636963, "genuineness": 4.6705241203308105, "identity": 0.5317543148994446, "hypothesis": "La porte 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_Emotional_Numbness/fb12a4bd417176a5c170aa0eecf2b803352b4f1a1a381f3ff05ff253200639c1.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "fb6d6822c77783be786399b82a2a19aeb4307ab1b1ac07fffeadb56a90cca504", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7c6346c607a04420b9ce49423e734401ee2c40659463ae2d8c94b17e4f2551d7", "generation_seconds_batch": 18.554787694942206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44457143545150757, "target_z": -0.017944325630476893, "ce": 5.792276382446289, "genuineness": 4.375550270080566, "identity": 0.6130097508430481, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/fb6d6822c77783be786399b82a2a19aeb4307ab1b1ac07fffeadb56a90cca504.mp3" }, { "id": "emo_Emotional_Numbness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-1", "key": "fbb0926973f6171be823092cb7e10d69a045ad4f36751323a29e88cfef1c194b", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "81282431a704ec5fc44232a7845c8e3f2f16ce32ee49b79d4b94a53e19074aa3", "generation_seconds_batch": 18.61741498496849, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7810611128807068, "target_z": 0.3320312427351379, "ce": 5.609594821929932, "genuineness": 4.394378662109375, "identity": 0.455894410610199, "hypothesis": "Ik 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_Emotional_Numbness/fbb0926973f6171be823092cb7e10d69a045ad4f36751323a29e88cfef1c194b.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": "fbf0da771a1af0ed667618defc231e418fb2ff6167f811faeb255a440cc601b8", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "76cd0e48ed77a3ca63634c534b3c7cdf451d1bf790fcba26cd12b6e8d4752d43", "generation_seconds_batch": 18.548494021059014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9726032018661499, "target_z": 0.5312499883762206, "ce": 5.772419452667236, "genuineness": 4.557555198669434, "identity": 0.46732205152511597, "hypothesis": "De sleutels liggen op de keukentafel. Ik keken de laag en de daarna en naast het raam. Neem ze mee als je weggaat.", "wer": 0.22727272727272727, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/fbf0da771a1af0ed667618defc231e418fb2ff6167f811faeb255a440cc601b8.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": "fc01153d841244758d32843109dd8bd5e87fdb647ffdcec55ea07549b6b2d3bc", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] I wrote the number on the envelope.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [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": "51dc8b7cd32783168e9a1ef60b6598308a885a860150fd4b3449c28249ab0766", "generation_seconds_batch": 18.50217580702156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29093870520591736, "target_z": -0.17773437475783793, "ce": 5.855817794799805, "genuineness": 4.532451152801514, "identity": 0.26070746779441833, "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_Emotional_Numbness/fc01153d841244758d32843109dd8bd5e87fdb647ffdcec55ea07549b6b2d3bc.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "fcf49f9e672b834d545b82eaae87b23105a4f62b23f892ff42d7f04e8e5a1f58", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6f5aeb165769d23a127453247d42a01f131cefefbb9f0c2844f6fc64bdf2afe1", "generation_seconds_batch": 26.16970719897654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.314411997795105, "target_z": -0.15332031552702588, "ce": 5.7128496170043945, "genuineness": 4.946669578552246, "identity": 0.609763503074646, "hypothesis": "La porte 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_Emotional_Numbness/fcf49f9e672b834d545b82eaae87b23105a4f62b23f892ff42d7f04e8e5a1f58.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "fcf6d5be500aa5dbfb5d89e5d4de6392aff64d8063b21e3aff36dd0a62206a30", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b142e7a0fdcc14a5b3a8dbffc3c7e854f7f3e77c062deb0a8510948993a3ed47", "generation_seconds_batch": 18.606724006938748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8599313497543335, "target_z": 0.41406245447353085, "ce": 5.71682071685791, "genuineness": 4.356721878051758, "identity": 0.41154393553733826, "hypothesis": "La puerta sigue ha dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/fcf6d5be500aa5dbfb5d89e5d4de6392aff64d8063b21e3aff36dd0a62206a30.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": "fd1860e276f484750938e9f9ef78bce229597ce4469e66d19dea8e73997983e7", "bucket": "emo_Emotional_Numbness", "phase": "heldout", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "52500d96357030820f65501a6c49387f1a4889418fe6f02256d2248e8aa15ac4", "generation_seconds_batch": 26.28667589998804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5740266442298889, "target_z": 0.11669921118243531, "ce": 5.839932441711426, "genuineness": 4.457139015197754, "identity": 0.5834075212478638, "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_Emotional_Numbness/fd1860e276f484750938e9f9ef78bce229597ce4469e66d19dea8e73997983e7.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "feade734eccf2552ccff5c34a82d6a9a2fae008216d311872fa0ccc31098e6b7", "bucket": "emo_Emotional_Numbness", "phase": "wording", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "75e1958cfd71170699e93d8259c763141ab6ddef2a291374389e2f616d2eff7b", "generation_seconds_batch": 23.116709231981076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 6.157639026641846, "genuineness": 4.570107460021973, "identity": 0.5279911160469055, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/feade734eccf2552ccff5c34a82d6a9a2fae008216d311872fa0ccc31098e6b7.mp3" }, { "id": "emo_Emotional_Numbness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-fr-0", "key": "ff14d863d0c4e78659a1011c9eb56c245d3d38a84abca478a00b09096bd3fc09", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La porte est encore ouverte.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b5d3063920a571ed850369a23c84efe1793168d860eeec025d610a1d0cf1645f", "generation_seconds_batch": 21.83808705001138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7190916538238525, "target_z": 0.26757816108214844, "ce": 5.708878040313721, "genuineness": 4.846253395080566, "identity": 0.6366579532623291, "hypothesis": "La porte 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_Emotional_Numbness/ff14d863d0c4e78659a1011c9eb56c245d3d38a84abca478a00b09096bd3fc09.mp3" }, { "id": "emo_Emotional_Numbness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-en-0", "key": "ff55a8b3836bceaef1b73fcc9a76741f5c1ec52222834eacc6768994120c9ee9", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] The door is still open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b0cb27e5318beb9aebbd1855d0b2456dff3a4c4c4eeefbcf7e3c2fa29794dd0c", "generation_seconds_batch": 24.26654276798945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10690805315971375, "target_z": -0.369140638803238, "ce": 6.260893821716309, "genuineness": 4.124508857727051, "identity": 0.3526012897491455, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ff55a8b3836bceaef1b73fcc9a76741f5c1ec52222834eacc6768994120c9ee9.mp3" }, { "id": "emo_Emotional_Numbness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-nl-0", "key": "ff7a4b41f3d40f7a9d72f78629809b6937c5cd2f38cb3a422d1058a6412783c8", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] De deur staat nog open.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7d0d1e14e08779ad66db4767ff7b3d3e18400ff6bf43cdc00ed265c770949264", "generation_seconds_batch": 24.022381752962247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4635847806930542, "target_z": 0.0018310397188570434, "ce": 5.879645347595215, "genuineness": 4.532451152801514, "identity": 0.5430893898010254, "hypothesis": "De deur 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_Emotional_Numbness/ff7a4b41f3d40f7a9d72f78629809b6937c5cd2f38cb3a422d1058a6412783c8.mp3" }, { "id": "emo_Emotional_Numbness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-1", "key": "ff9ad86cfe92bb26d4647a36aa25477bcb179e0aeedd1059f58912ad8a36f2a6", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] He encontrado la cajita.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2d22c411d1f1d3f834c3d916b5acce474515aecfbbcb9ad5910abe779c3d20a0", "generation_seconds_batch": 18.875411252025515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3538471460342407, "target_z": -0.11230467866108444, "ce": 5.935244083404541, "genuineness": 4.796044826507568, "identity": 0.6371844410896301, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ff9ad86cfe92bb26d4647a36aa25477bcb179e0aeedd1059f58912ad8a36f2a6.mp3" }, { "id": "emo_Emotional_Numbness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-es-0", "key": "ffaaed50ae9882292f488f0f05be882f9f7928ef8801773fc1269929ccbf3fd4", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] La puerta sigue abierta.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4488695f7d6ef5868eea73324f5c8cc74383ad5cb2923884ee044211f0915acc", "generation_seconds_batch": 23.722369353985414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7266030311584473, "target_z": 0.2753905806843412, "ce": 5.919358730316162, "genuineness": 4.394378662109375, "identity": 0.755597710609436, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ffaaed50ae9882292f488f0f05be882f9f7928ef8801773fc1269929ccbf3fd4.mp3" }, { "id": "emo_Emotional_Numbness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Emotional_Numbness-de-0", "key": "ffdf1854c0dcdbfe4df1c7ad0ba24538e6aa6dab7d1718b3ebaff747acec2271", "bucket": "emo_Emotional_Numbness", "phase": "grid", "candidate": "manual-53d14c32a3a7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Maintain a consistently flat, almost monotone pitch contour throughout the entire utterance, devoid of any natural inflections.\nSCRIPT:\n(Initiate with a breathy, minimal vocal projection that suggests detachment.) [3.2 seconds duration] Die Tür ist noch offen.\n(Sustain a mid-range, unchanging vocal placement across the core of the statement.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the closing words with the same low energy, ensuring no rise or fall.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "09f31a6ab0271018af01564773f5335c3fd015ee882a2a52a5bc4fcfaa19c883", "generation_seconds_batch": 26.22193914593663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33882421255111694, "target_z": -0.12792970384593974, "ce": 5.824047088623047, "genuineness": 4.808597087860107, "identity": 0.6143755912780762, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Emotional_Numbness/ffdf1854c0dcdbfe4df1c7ad0ba24538e6aa6dab7d1718b3ebaff747acec2271.mp3" }, { "key": "original-emo_Emotional_Numbness-de-0-seed1701-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "152450db5453d3db19c7f3a2f94ec70ae8e0cf64e21ef6786731845c4d7472c4", "task_id": "emo_Emotional_Numbness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.14822107553482056, "target_z": -0.3261718660400034, "ce": 6.141753673553467, "genuineness": 4.6203155517578125, "identity": 0.5572900772094727, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/e093ae7c6215ea3797367880.mp3" }, { "key": "original-emo_Emotional_Numbness-de-0-seed1701-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "7763c55fd7572f64e0e7bdd59ada85673e36c85965fb619330aca38cec9d5439", "task_id": "emo_Emotional_Numbness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.1463432013988495, "target_z": -0.32812500193729655, "ce": 6.229123115539551, "genuineness": 4.256305694580078, "identity": 0.7028655409812927, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/257133423d5dc267332b5ace.mp3" }, { "key": "original-emo_Emotional_Numbness-de-0-seed1701-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "5905fa69fbd6e96daf7bf196d01a95435200d5cd9fae0978a2dff31a29f6a1f1", "task_id": "emo_Emotional_Numbness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.1388317346572876, "target_z": -0.3359375145297242, "ce": 6.213237762451172, "genuineness": 4.381826400756836, "identity": 0.5697898864746094, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/b9aec3954b2939cecee67dce.mp3" }, { "key": "original-emo_Emotional_Numbness-de-0-seed1701-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "69fa3d15ea70d47cf61fd0785c302562b0cc18dd3cead113ec8fc3d861b56dd8", "task_id": "emo_Emotional_Numbness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.15385466814041138, "target_z": -0.3203124893448689, "ce": 6.205295085906982, "genuineness": 4.607763767242432, "identity": 0.6551122665405273, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/0917775f3e150c40f0200fd2.mp3" }, { "key": "original-emo_Emotional_Numbness-de-0-seed1702-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "e90856b2f441d942c44bf93e8e10eea4bdd7baf564193fc507aa5c01b1eab172", "task_id": "emo_Emotional_Numbness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.15009891986846924, "target_z": -0.32421876113945525, "ce": 6.324435234069824, "genuineness": 4.325342178344727, "identity": 0.48232215642929077, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/f4c1d0ee3b8ce3df236704ff.mp3" }, { "key": "original-emo_Emotional_Numbness-de-0-seed1702-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "7ddc8622d65c0a4be1c387597f4f95a4216cea2a09688cc6398c0631e61b274f", "task_id": "emo_Emotional_Numbness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.17263329029083252, "target_z": -0.3007812543589173, "ce": 6.23706579208374, "genuineness": 4.469690799713135, "identity": 0.6289664506912231, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/b69965efec6eadcd8bdaf53c.mp3" }, { "key": "original-emo_Emotional_Numbness-de-0-seed1702-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "9d0e8d5f029a5ccb8065c367107a68b387333d3840c0bbef567fa84e6e4e4f15", "task_id": "emo_Emotional_Numbness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.15385466814041138, "target_z": -0.3203124893448689, "ce": 6.197352409362793, "genuineness": 4.331617832183838, "identity": 0.523919403553009, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/875e4e9c6745ca3e690c095a.mp3" }, { "key": "original-emo_Emotional_Numbness-de-0-seed1702-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "8e779088e411dbfc210ac469ffb0384b22c55e3978ce0aab139f39a30772cd8c", "task_id": "emo_Emotional_Numbness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.12568670511245728, "target_z": -0.3496093728205414, "ce": 6.181467056274414, "genuineness": 4.381826400756836, "identity": 0.44390586018562317, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/6141d8e73b34f182b5980b4a.mp3" }, { "key": "original-emo_Emotional_Numbness-de-1-seed1701-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "95cbf6a460eca374f1e5396270dce6344106311e895d516a51d1990aaef50d33", "task_id": "emo_Emotional_Numbness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.05808362364768982, "target_z": -0.4199218621654103, "ce": 6.427689552307129, "genuineness": 4.18726921081543, "identity": 0.6539352536201477, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/849220efd3699fe3ebab291b.mp3" }, { "key": "original-emo_Emotional_Numbness-de-1-seed1701-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "4652d58e85a97a6460987e3d08bd9732301bf27e74376652ee7855bab5ee55c9", "task_id": "emo_Emotional_Numbness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.04681643843650818, "target_z": -0.4316406155556793, "ce": 6.38003396987915, "genuineness": 4.093128204345703, "identity": 0.6743998527526855, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/901820cee9ffc1df6d2c13b8.mp3" }, { "key": "original-emo_Emotional_Numbness-de-1-seed1701-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "8f7d201079af4e31a9e225744145de8132123d46830342b12c4fda1e4e49fdaa", "task_id": "emo_Emotional_Numbness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.03742709755897522, "target_z": -0.44140626404540007, "ce": 6.403861999511719, "genuineness": 4.086852550506592, "identity": 0.6010868549346924, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/704b1d5af9322b3ec45c69bb.mp3" }, { "key": "original-emo_Emotional_Numbness-de-1-seed1701-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "68497348c073c65b265197f5a48c0807e98a9402bffd75dee374898b9d69449b", "task_id": "emo_Emotional_Numbness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.0881294310092926, "target_z": -0.38867187378918966, "ce": 6.41180419921875, "genuineness": 4.3504462242126465, "identity": 0.574993908405304, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/f8b25dc791d879f25b22c3c2.mp3" }, { "key": "original-emo_Emotional_Numbness-de-1-seed1702-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "d8224a9b078eb876b77608fcf2c49d415f87507e64849b2744774c4680dee3bc", "task_id": "emo_Emotional_Numbness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.0881294310092926, "target_z": -0.38867187378918966, "ce": 6.435632705688477, "genuineness": 4.419482707977295, "identity": 0.5302039384841919, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/54b354bfa7ca0125b4166191.mp3" }, { "key": "original-emo_Emotional_Numbness-de-1-seed1702-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "5154f8e787ddad9db5309c36c2c8e6068248d043fdf68db72249979ea49b3a34", "task_id": "emo_Emotional_Numbness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.05432787537574768, "target_z": -0.4238281339599966, "ce": 6.38003396987915, "genuineness": 4.268857479095459, "identity": 0.6181795597076416, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/40a0c52eda381d642c393fc4.mp3" }, { "key": "original-emo_Emotional_Numbness-de-1-seed1702-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "281f992a63fb69d615ec0410e7c890f1a1e8acd0f4ed5938a073a29267ca3156", "task_id": "emo_Emotional_Numbness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.07498437166213989, "target_z": -0.4023437630767518, "ce": 6.356205940246582, "genuineness": 4.268857479095459, "identity": 0.5223163962364197, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/cf727f4d363abb5bdbcbeba1.mp3" }, { "key": "original-emo_Emotional_Numbness-de-1-seed1702-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "008f557c001f94f1e3f607b25eb1bebe9734c7bc5883fab97c692012e031eb91", "task_id": "emo_Emotional_Numbness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.05620574951171875, "target_z": -0.42187499806270345, "ce": 6.23706579208374, "genuineness": 4.256305694580078, "identity": 0.5101099610328674, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/de/38373ae4fd9ffe8a0cad7660.mp3" }, { "key": "original-emo_Emotional_Numbness-en-0-seed1701-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "f2e7c0550488669d72735a9cbdacaf6585aa3b060f5aaa3544ffda2b004d36cb", "task_id": "emo_Emotional_Numbness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.14258748292922974, "target_z": -0.3320312427351379, "ce": 6.2767791748046875, "genuineness": 4.281409740447998, "identity": 0.29360300302505493, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/dae7291a33ba7ac0d3ba253a.mp3" }, { "key": "original-emo_Emotional_Numbness-en-0-seed1701-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "4d5a02d3b13d3be74e94f4e3716b5ae863e260816aea001169ee5445080412de", "task_id": "emo_Emotional_Numbness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.14822107553482056, "target_z": -0.3261718660400034, "ce": 6.1894097328186035, "genuineness": 3.9299514293670654, "identity": 0.38369882106781006, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/5e0ee8be03bfa0f5aed13378.mp3" }, { "key": "original-emo_Emotional_Numbness-en-0-seed1701-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "9d88582432f8b9888b24ec67244bf870b23bd762af6197de3bebfb47209351e0", "task_id": "emo_Emotional_Numbness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.09939661622047424, "target_z": -0.37695312039892065, "ce": 6.23706579208374, "genuineness": 3.6914620399475098, "identity": 0.4293699860572815, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/a94ae21bcd15e99c38fa6ec5.mp3" }, { "key": "original-emo_Emotional_Numbness-en-0-seed1701-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "2338d55d912d2a06fa4cd64ff826b2a18f0b713c4a78ac503069a330a1707bc0", "task_id": "emo_Emotional_Numbness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.10127449035644531, "target_z": -0.3749999845016275, "ce": 6.1894097328186035, "genuineness": 3.6663577556610107, "identity": 0.38036125898361206, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/b5beed6c6c32c237ededcd48.mp3" }, { "key": "original-emo_Emotional_Numbness-en-0-seed1702-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "3e99027c1bf9c3945813bfabee245438361bb56b70c8ee759b7b28189672a339", "task_id": "emo_Emotional_Numbness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.06371721625328064, "target_z": -0.4140624854702758, "ce": 6.268836498260498, "genuineness": 3.773050308227539, "identity": 0.35629594326019287, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/e5c8781501fadf2d445508db.mp3" }, { "key": "original-emo_Emotional_Numbness-en-0-seed1702-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "81d9368b53654162be713c7ebeb767bf30ec1e3d6abfe1160deb1578ccc92aba", "task_id": "emo_Emotional_Numbness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.10690805315971375, "target_z": -0.369140638803238, "ce": 6.252951145172119, "genuineness": 3.7918784618377686, "identity": 0.2794138789176941, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/3d555179f034325e736e25e8.mp3" }, { "key": "original-emo_Emotional_Numbness-en-0-seed1702-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "66fb97b11e35225a469853a9537b2327f7d5c9ab03fdfc8781bf3eac5a04373a", "task_id": "emo_Emotional_Numbness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.10127449035644531, "target_z": -0.3749999845016275, "ce": 6.078212261199951, "genuineness": 3.9425034523010254, "identity": 0.3759118914604187, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/fd9b98c2709a3305347b4efe.mp3" }, { "key": "original-emo_Emotional_Numbness-en-0-seed1702-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "bb33f617b073c132ae4842e6132d261babe6037e675e91aef54eb009bdf37d6e", "task_id": "emo_Emotional_Numbness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.09000730514526367, "target_z": -0.3867187378918965, "ce": 6.316492557525635, "genuineness": 3.9550557136535645, "identity": 0.4397072494029999, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/3fd89927f1d4ded42b8763e2.mp3" }, { "key": "original-emo_Emotional_Numbness-en-1-seed1701-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "26be7d5666f6a222f07ecdff736820dd6e2089425e82489f05cb90c5257e8cc2", "task_id": "emo_Emotional_Numbness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.05808362364768982, "target_z": -0.4199218621654103, "ce": 6.403861999511719, "genuineness": 4.444586753845215, "identity": 0.5894396305084229, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/9911c84fc113d87e00803b71.mp3" }, { "key": "original-emo_Emotional_Numbness-en-1-seed1701-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "7c87dc0c2376a2e8989c7c1bf2ffdedc943baa591fdc4b6d23f41af631d50f04", "task_id": "emo_Emotional_Numbness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.05808362364768982, "target_z": -0.4199218621654103, "ce": 6.3641486167907715, "genuineness": 4.375550270080566, "identity": 0.5076268315315247, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/e38c4b37922c6dfe7d9c3d7d.mp3" }, { "key": "original-emo_Emotional_Numbness-en-1-seed1701-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "2dd8df39d35ab8d5013f960e908857e91e94abda2c22c68e353d09f007c6eaf7", "task_id": "emo_Emotional_Numbness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.011137008666992188, "target_z": -0.4687500116237794, "ce": 6.443574905395508, "genuineness": 4.356721878051758, "identity": 0.4316793382167816, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/d70324e5ebfca9aebb15c363.mp3" }, { "key": "original-emo_Emotional_Numbness-en-1-seed1701-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "439c3fc97dc5c3f8bb1d0a147cb9806f8ded9f3c5e24ee0b76be82e40f6dac87", "task_id": "emo_Emotional_Numbness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.020526349544525146, "target_z": -0.45898436313405855, "ce": 6.348263263702393, "genuineness": 4.3127899169921875, "identity": 0.37821412086486816, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/e071bbfcdd2e93ef5d4888b9.mp3" }, { "key": "original-emo_Emotional_Numbness-en-1-seed1702-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "f2aa973f0e44ccbd0e9dffd328d347d3106d2f2c4e4714ee0f83f542a51041f9", "task_id": "emo_Emotional_Numbness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.06559506058692932, "target_z": -0.4121093805697276, "ce": 6.300607204437256, "genuineness": 4.557555198669434, "identity": 0.40497785806655884, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/50e6c2f817a9c58199b29fef.mp3" }, { "key": "original-emo_Emotional_Numbness-en-1-seed1702-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "64c2aed26179943dfccb3d91cea4f6d15c26ede644ff6600e0f4c66aef34d77e", "task_id": "emo_Emotional_Numbness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.05808362364768982, "target_z": -0.4199218621654103, "ce": 6.507116317749023, "genuineness": 4.482243061065674, "identity": 0.26876315474510193, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/7088a030a898b8390660f573.mp3" }, { "key": "original-emo_Emotional_Numbness-en-1-seed1702-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "b543efa0dfe47730d173ba83a1fd578f9f49ce59a23840923b8cbc0da4c786ba", "task_id": "emo_Emotional_Numbness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.03554925322532654, "target_z": -0.44335936894594824, "ce": 6.3641486167907715, "genuineness": 4.400654315948486, "identity": 0.298530250787735, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/e04c7483bc25256b063a45e9.mp3" }, { "key": "original-emo_Emotional_Numbness-en-1-seed1702-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "60df1d931db2aaa0a32c2cd66c059296ae35c7deb05efa4702bfd6650e95cf0b", "task_id": "emo_Emotional_Numbness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.06559506058692932, "target_z": -0.4121093805697276, "ce": 6.332377910614014, "genuineness": 4.18726921081543, "identity": 0.46492621302604675, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/en/0823822604cdc63982c06763.mp3" }, { "key": "original-emo_Emotional_Numbness-es-0-seed1701-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "67a06861326ce782fedf299d069690cd90536b9101259c043eedd115986d6ea4", "task_id": "emo_Emotional_Numbness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.08249583840370178, "target_z": -0.39453125048432414, "ce": 6.046441555023193, "genuineness": 4.18099308013916, "identity": 0.4844077229499817, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/0f2775a17addfa94416908ae.mp3" }, { "key": "original-emo_Emotional_Numbness-es-0-seed1701-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "5d14e2df334bedd845e9a846f24ce31d80b3ee335cddcbe48b2c8fc8361c139f", "task_id": "emo_Emotional_Numbness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.11817523837089539, "target_z": -0.357421885412969, "ce": 6.252951145172119, "genuineness": 4.356721878051758, "identity": 0.46259593963623047, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/93a127fe6e6e92565a879158.mp3" }, { "key": "original-emo_Emotional_Numbness-es-0-seed1701-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "7966e5941710af2b0d7ca487bbb410dd5656cd2cbf5fe975be53c9d0a90ca12c", "task_id": "emo_Emotional_Numbness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.2637096643447876, "target_z": -0.20605470578323629, "ce": 6.181467056274414, "genuineness": 4.086852550506592, "identity": 0.48655813932418823, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/e4f08379b395721c0f8d2651.mp3" }, { "key": "original-emo_Emotional_Numbness-es-0-seed1701-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "f767c24810c3259278dfd2c953bbc846474bf3b25f601338b7d9c2ef59e00169", "task_id": "emo_Emotional_Numbness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.2787325978279114, "target_z": -0.190429680598381, "ce": 6.1020402908325195, "genuineness": 4.143336772918701, "identity": 0.41013744473457336, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/e26ea64d4801849ff8a12c97.mp3" }, { "key": "original-emo_Emotional_Numbness-es-0-seed1702-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "f649791579eb00de659674525964fd495e6d5f0448afd81bac12ac6b38d2366b", "task_id": "emo_Emotional_Numbness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.15385466814041138, "target_z": -0.3203124893448689, "ce": 6.149696350097656, "genuineness": 4.193545341491699, "identity": 0.4987650215625763, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/ecb3d735ba2e48d8291a2862.mp3" }, { "key": "original-emo_Emotional_Numbness-es-0-seed1702-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "63c166e2d497bbd1f61206290b6355e5f433407006133412485b524079b28b46", "task_id": "emo_Emotional_Numbness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.20831269025802612, "target_z": -0.26367188928756213, "ce": 5.974957466125488, "genuineness": 4.093128204345703, "identity": 0.45410066843032837, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/89c022f3fead010a5716fbf4.mp3" }, { "key": "original-emo_Emotional_Numbness-es-0-seed1702-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "fb1a0158762fd958aba1ec8a4c0b5ce85a058783c399857214f2132a9695ef56", "task_id": "emo_Emotional_Numbness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.15573251247406006, "target_z": -0.3183593844443207, "ce": 5.772419452667236, "genuineness": 4.344170093536377, "identity": 0.7021714448928833, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/cb90c2b715ef865ae1d39d22.mp3" }, { "key": "original-emo_Emotional_Numbness-es-0-seed1702-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "9a9c62313c4c4bf0634f9aefdb343824c23220730efa5a717ed0221917557b7d", "task_id": "emo_Emotional_Numbness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 5.974957466125488, "genuineness": 4.15588903427124, "identity": 0.5333327054977417, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/960bc079c2d2cddb4a42b97e.mp3" }, { "key": "original-emo_Emotional_Numbness-es-1-seed1701-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "95539b795eced96d6d0dcbedf939de66697e514f9da06b6a096a51f327c8a153", "task_id": "emo_Emotional_Numbness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.07122865319252014, "target_z": -0.40625000387459315, "ce": 6.165581703186035, "genuineness": 4.362998008728027, "identity": 0.7236531376838684, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/11340041167441612930b7f4.mp3" }, { "key": "original-emo_Emotional_Numbness-es-1-seed1701-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "ca9a40672eee9e11e9ed90b3b2f47d4c4f154479865bc37cc78bba71b0dbcf6e", "task_id": "emo_Emotional_Numbness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.1313202977180481, "target_z": -0.34374999612540685, "ce": 6.070269584655762, "genuineness": 4.419482707977295, "identity": 0.6408010125160217, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/bb33f32d4fb9dff6e9c96585.mp3" }, { "key": "original-emo_Emotional_Numbness-es-1-seed1701-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "fa40d22867511ac9c8387945da43918bb7e1684a5f56cce03b212e285ab452c2", "task_id": "emo_Emotional_Numbness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.07122865319252014, "target_z": -0.40625000387459315, "ce": 6.133810997009277, "genuineness": 4.6956281661987305, "identity": 0.661201536655426, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/2e6a56d37531027040c88088.mp3" }, { "key": "original-emo_Emotional_Numbness-es-1-seed1701-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "72ebc08e5e4a285868d33d6d56aa11e21f7e48b6ddb0f5283fd9f8e6a1d3aea9", "task_id": "emo_Emotional_Numbness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.09000730514526367, "target_z": -0.3867187378918965, "ce": 6.1894097328186035, "genuineness": 4.432034492492676, "identity": 0.5614615678787231, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/90ca5a41267b6bfab2ddb25b.mp3" }, { "key": "original-emo_Emotional_Numbness-es-1-seed1702-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "efee756de4063f07b072c09d5e462605f8be38e3e7e4c05b4a67eb1336126c65", "task_id": "emo_Emotional_Numbness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.14070960879325867, "target_z": -0.3339843786324311, "ce": 6.165581703186035, "genuineness": 4.545003414154053, "identity": 0.608667254447937, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/45de2290fefe7e852a2a4454.mp3" }, { "key": "original-emo_Emotional_Numbness-es-1-seed1702-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "b2c379b1b01ea26a93890d1f08181eaf069cefc7b7295de0e4a7e452827c3c69", "task_id": "emo_Emotional_Numbness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.08437371253967285, "target_z": -0.392578114587031, "ce": 6.268836498260498, "genuineness": 4.595211505889893, "identity": 0.6563480496406555, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/a9c3c1ef4c7b9943a9f0ebda.mp3" }, { "key": "original-emo_Emotional_Numbness-es-1-seed1702-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "dca246dc6b2d4e3f3261f4d2a8c0a6f53d8e2361dc5ff54056744d078a05d563", "task_id": "emo_Emotional_Numbness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.08061796426773071, "target_z": -0.3964843863816173, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.5330531001091003, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/17555494fd70d79ee4202e9c.mp3" }, { "key": "original-emo_Emotional_Numbness-es-1-seed1702-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "807408da7d5fab1a595691ab3ce5e656e2fca034a6e75af8305aeb5da459bad8", "task_id": "emo_Emotional_Numbness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.1519767940044403, "target_z": -0.32226562524216207, "ce": 5.990842819213867, "genuineness": 4.545003414154053, "identity": 0.803766131401062, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Emotional_Numbness/es/2fd86c7d69ade9f52855ff07.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-0-seed1701-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "8dea40b64717ec728b3d6f010a765d528bec7228f385d99936c928e3b0938534", "task_id": "emo_Emotional_Numbness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.07122865319252014, "target_z": -0.40625000387459315, "ce": 6.173524379730225, "genuineness": 4.6203155517578125, "identity": 0.7367044687271118, "hypothesis": "La porte 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_Emotional_Numbness/fr/f450c3868d0612f58a399b73.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-0-seed1701-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "84d045acd74d7fd0c805ee1647ff0bdf28556cc0323ffbce62b80a858cf6adc5", "task_id": "emo_Emotional_Numbness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.1238088309764862, "target_z": -0.3515625087178345, "ce": 6.205295085906982, "genuineness": 4.482243061065674, "identity": 0.7635794281959534, "hypothesis": "La porte 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_Emotional_Numbness/fr/1f265d7c561d96e8b238bdf4.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-0-seed1701-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "872d297cc9fcd283643edba132d1138b3f3a154b990af8778ed3834dd8dc12d2", "task_id": "emo_Emotional_Numbness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.24023638665676117, "target_z": -0.23046874951567586, "ce": 6.213237762451172, "genuineness": 4.7081804275512695, "identity": 0.7355512380599976, "hypothesis": "La porte 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_Emotional_Numbness/fr/408162239498c0bb02d7ba9d.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-0-seed1701-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "23dfb499fe62b4abb0c68f38887b9f2e2cc965bc955d1afa45fa2159c3b58d08", "task_id": "emo_Emotional_Numbness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.09564089775085449, "target_z": -0.380859361196762, "ce": 6.1020402908325195, "genuineness": 4.281409740447998, "identity": 0.7574201822280884, "hypothesis": "La porte 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_Emotional_Numbness/fr/3071a068b8e21edd052a7341.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-0-seed1702-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "ce5f61c64c8073cc0121f14db699af3d6d2375bac3b8414aa78eb7575ead7dbc", "task_id": "emo_Emotional_Numbness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.07122865319252014, "target_z": -0.40625000387459315, "ce": 6.292664527893066, "genuineness": 4.482243061065674, "identity": 0.7003233432769775, "hypothesis": "La porte 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_Emotional_Numbness/fr/0651864cfe9cb44ed5480b29.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-0-seed1702-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "a18000d764a13669b4678aeb76c622a5e24d649d510a5e68fe854ea513da06fa", "task_id": "emo_Emotional_Numbness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.07874011993408203, "target_z": -0.3984374912821655, "ce": 6.157639026641846, "genuineness": 4.406930446624756, "identity": 0.8234269022941589, "hypothesis": "La porte 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_Emotional_Numbness/fr/8f5432c627ba520102e3eb2a.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-0-seed1702-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "3aa3318ce0408c44c4e42e8400a270a21c6ee3096efa2f4d619f882c593a3bc0", "task_id": "emo_Emotional_Numbness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.13695389032363892, "target_z": -0.3378906194302724, "ce": 6.09409761428833, "genuineness": 4.507347106933594, "identity": 0.6218621134757996, "hypothesis": "La porte 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_Emotional_Numbness/fr/e8ad894f3d1ea0f15e440879.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-0-seed1702-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "559628b2a24dcf8b4ae05a19b2fdef40a492a5ccd8575360f2926de66c998c02", "task_id": "emo_Emotional_Numbness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.12944242358207703, "target_z": -0.34570313202270003, "ce": 6.284721851348877, "genuineness": 4.7834930419921875, "identity": 0.6665711402893066, "hypothesis": "La porte 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_Emotional_Numbness/fr/46f8da56d983e6a83db92333.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-1-seed1701-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "9377a271d9aa8d2f2108d110e6853c5f841ca0d5413e58a7df32a8e58c08e06d", "task_id": "emo_Emotional_Numbness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.04493856430053711, "target_z": -0.4335937514529724, "ce": 6.109982967376709, "genuineness": 4.570107460021973, "identity": 0.7397271990776062, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/fr/36ae198e2a44cd0115c62896.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-1-seed1701-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "61f7b946f16d4eb45116d6d95f00b048f9f8385bbd08d29692f8e338bcd9c27d", "task_id": "emo_Emotional_Numbness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.07498437166213989, "target_z": -0.4023437630767518, "ce": 6.109982967376709, "genuineness": 4.419482707977295, "identity": 0.7658731937408447, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/fr/74081316b8d9f0293569de63.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-1-seed1701-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "2c20740d8f05056b6fb140f1b3aaa48db34b79a7c149705eb9e34d8ddfab0908", "task_id": "emo_Emotional_Numbness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.1519767940044403, "target_z": -0.32226562524216207, "ce": 6.24500846862793, "genuineness": 4.607763767242432, "identity": 0.6598822474479675, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/fr/0389c545caeb371460017196.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-1-seed1701-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "489bcc638dae63f3939540fb265a388f94ff7ceab786a3b0c778f153e3304917", "task_id": "emo_Emotional_Numbness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.022404193878173828, "target_z": -0.4570312582335104, "ce": 6.284721851348877, "genuineness": 4.532451152801514, "identity": 0.7177759408950806, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/fr/3e5d39906157b2dc1d7d2780.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-1-seed1702-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "ef98ec6d9afc50f9a063bb68586ec0a63462899aba49f06b1c92e708301b662d", "task_id": "emo_Emotional_Numbness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.04869428277015686, "target_z": -0.4296875106551311, "ce": 6.133810997009277, "genuineness": 4.319066047668457, "identity": 0.7599406242370605, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/fr/a3a3d350d131de8f88b0ac4e.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-1-seed1702-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "bbaf1f7709ddd601a1b12ec27de2270cf4777da10499e1bc6481c99c75f4b9df", "task_id": "emo_Emotional_Numbness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.05620574951171875, "target_z": -0.42187499806270345, "ce": 6.038498878479004, "genuineness": 4.457139015197754, "identity": 0.7772851586341858, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/fr/f3ad46dbfa6b94bf7102c74d.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-1-seed1702-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "a477e5ef1603059b69361ee6fba06298b9a0bdbddab523878801a11ca5c6b43e", "task_id": "emo_Emotional_Numbness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.17075541615486145, "target_z": -0.3027343902562104, "ce": 6.1894097328186035, "genuineness": 4.720732688903809, "identity": 0.8068757653236389, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/fr/e5b6d28077fe7d87a2546ac5.mp3" }, { "key": "original-emo_Emotional_Numbness-fr-1-seed1702-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "79a0be7a52e0aaea12cd1910a4734617eeadc555b28bf38c497f3f1f8ac23c16", "task_id": "emo_Emotional_Numbness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.11066380143165588, "target_z": -0.3652343670086517, "ce": 6.229123115539551, "genuineness": 4.7081804275512695, "identity": 0.803817093372345, "hypothesis": "J'ai trouvé la 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_Emotional_Numbness/fr/8c865e283c602514b938f57f.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-0-seed1701-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "c822db7f04dfc4b34ee5127559029b0c1ef703f2e59e7c9db079df94a5976c9a", "task_id": "emo_Emotional_Numbness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.18390047550201416, "target_z": -0.2890625009686483, "ce": 6.0305562019348145, "genuineness": 4.13078498840332, "identity": 0.5641341209411621, "hypothesis": "De deur 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_Emotional_Numbness/nl/befb706e19adb6ee81ad11fd.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-0-seed1701-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "3557f9f90906589b15bd8b390b1b5ce78bd385ae0eb214446c7877bab18532a2", "task_id": "emo_Emotional_Numbness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.17075541615486145, "target_z": -0.3027343902562104, "ce": 6.125868320465088, "genuineness": 4.331617832183838, "identity": 0.7379871606826782, "hypothesis": "De deur 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_Emotional_Numbness/nl/d059a58b8adeef4e4034979a.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-0-seed1701-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "4b6fbffa3048b9bc0ab854618e8f94c52fbb682764cd001c2a1d5c8216550472", "task_id": "emo_Emotional_Numbness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.1519767940044403, "target_z": -0.32226562524216207, "ce": 6.149696350097656, "genuineness": 4.319066047668457, "identity": 0.7307047843933105, "hypothesis": "De deur 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_Emotional_Numbness/nl/46e3a55d0ee6868e3bd59440.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-0-seed1701-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "ef1228713ababa91ea83f4fac4a353d862b2b443cc22e3a479efd4edaeba6d6a", "task_id": "emo_Emotional_Numbness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.0881294310092926, "target_z": -0.38867187378918966, "ce": 6.1894097328186035, "genuineness": 4.20609712600708, "identity": 0.6835357546806335, "hypothesis": "De deur 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_Emotional_Numbness/nl/e0d57638240bc254db0ad8cf.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-0-seed1702-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "052182d55241065b7e786a971aa7cd2aab279d5e8e07551c6d909006c18b4253", "task_id": "emo_Emotional_Numbness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.3069005608558655, "target_z": -0.16113279712270856, "ce": 5.959072113037109, "genuineness": 4.105680465698242, "identity": 0.6489324569702148, "hypothesis": "De deur 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_Emotional_Numbness/nl/89e1ae748f9f63fece46235d.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-0-seed1702-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "6636ad7e8b0ce79e94c3ae61948cd684b207fb4127d0e1917696fb59aa129e34", "task_id": "emo_Emotional_Numbness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.13695389032363892, "target_z": -0.3378906194302724, "ce": 6.125868320465088, "genuineness": 4.193545341491699, "identity": 0.71727055311203, "hypothesis": "De deur 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_Emotional_Numbness/nl/bb9b2c201d1919c301d05df1.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-0-seed1702-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "94e1c8e34d8d8f267963156f7717a79f7da8563f617bc4adeacf67fed32b8cd7", "task_id": "emo_Emotional_Numbness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.23366385698318481, "target_z": -0.23730469415945693, "ce": 6.0146708488464355, "genuineness": 4.319066047668457, "identity": 0.7693200707435608, "hypothesis": "De deur 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_Emotional_Numbness/nl/88d499cdbbfcab671342c82c.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-0-seed1702-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "a44a37ab98ff40059dc163d064a641768883fa560ed09f14512ff2ce4311c624", "task_id": "emo_Emotional_Numbness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.1594882607460022, "target_z": -0.3144531126497344, "ce": 6.086154937744141, "genuineness": 4.13078498840332, "identity": 0.7095677852630615, "hypothesis": "De deur 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_Emotional_Numbness/nl/226e2d824b54c099f106fa88.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-1-seed1701-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "010464173f272e7c5439711bb2d0d9cdc31d3709d58cc103723a93133333afe8", "task_id": "emo_Emotional_Numbness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.16512185335159302, "target_z": -0.30859373595459993, "ce": 6.149696350097656, "genuineness": 4.356721878051758, "identity": 0.7747070789337158, "hypothesis": "Ik 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_Emotional_Numbness/nl/ac6ccde8793347986363ac0e.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-1-seed1701-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "07eb3eaebbd9a71e96fad84f16edec4710e9443cea1160b9fd67f3b861aca6f0", "task_id": "emo_Emotional_Numbness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.22145774960517883, "target_z": -0.25, "ce": 6.109982967376709, "genuineness": 4.319066047668457, "identity": 0.7397264242172241, "hypothesis": "Ik 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_Emotional_Numbness/nl/5dbae0768d3bed56d2fda882.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-1-seed1701-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "a315398d5c78fcdf2793aff53fc0ed55407af85d9305b12813c2bd8d031f62ba", "task_id": "emo_Emotional_Numbness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.17263329029083252, "target_z": -0.3007812543589173, "ce": 6.109982967376709, "genuineness": 4.124508857727051, "identity": 0.6617995500564575, "hypothesis": "Ik 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_Emotional_Numbness/nl/b205203117c2375be1fdd3f2.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-1-seed1701-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "c56a9c725ceff55b8ec0ba0c79855f52feee531bfbc878a5760815b9c8b62bc3", "task_id": "emo_Emotional_Numbness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.1745111644268036, "target_z": -0.2988281184616241, "ce": 5.95112943649292, "genuineness": 4.030367851257324, "identity": 0.661308228969574, "hypothesis": "Ik 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_Emotional_Numbness/nl/9aa069de3e6e420476138675.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-1-seed1702-scale0.0", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "416438716952d37422c6dac0d079840858c43703356b5cd1896dfc9af02505e7", "task_id": "emo_Emotional_Numbness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.14070960879325867, "target_z": -0.3339843786324311, "ce": 6.054384231567383, "genuineness": 4.18099308013916, "identity": 0.5634607076644897, "hypothesis": "Ik 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_Emotional_Numbness/nl/144871032a351a833f268ac5.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-1-seed1702-scale0.5", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "a7cab83afc20c03c6c759270fd93f2e73e0b7fad34ef9bc57c54cb0eeb9d5691", "task_id": "emo_Emotional_Numbness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.16887757182121277, "target_z": -0.3046874951567586, "ce": 6.284721851348877, "genuineness": 4.400654315948486, "identity": 0.6160982847213745, "hypothesis": "Ik 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_Emotional_Numbness/nl/b2c7ad70edb14c5adf5717d5.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-1-seed1702-scale0.75", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "fd1963d4a9a697245f56e619bf1f80f9b31f979e2856b33a4f524fa1b8ed7fbc", "task_id": "emo_Emotional_Numbness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.20080125331878662, "target_z": -0.2714843708832448, "ce": 6.133810997009277, "genuineness": 4.400654315948486, "identity": 0.553774356842041, "hypothesis": "Ik 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_Emotional_Numbness/nl/b61f428fa97646ae0792f71f.mp3" }, { "key": "original-emo_Emotional_Numbness-nl-1-seed1702-scale1.0", "bucket": "emo_Emotional_Numbness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "bf823decce31444b1b444708f524829abb4f1a961631f5303319361d9f934e28", "mp3_sha256": "58e5d2742eaebe39f3e6e5e3ca214f46f11a90901054e6b576730d508eeb4d63", "task_id": "emo_Emotional_Numbness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Emotional Numbness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Emotional Numbness. 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 Emotional Numbness. 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 Emotional Numbness. 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": 0.17075541615486145, "target_z": -0.3027343902562104, "ce": 6.157639026641846, "genuineness": 4.231201171875, "identity": 0.5656201839447021, "hypothesis": "Ik 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_Emotional_Numbness/nl/f02b059e4d61493adc8b9d0a.mp3" } ], "source_standard_audio_unchanged": true }