{ "complete": true, "report": { "bucket": "emo_Sourness", "label": "Intense Sourness", "definition": { "id": "emo_Sourness", "category": "emotion", "head": "emo_Sourness", "pole": "high", "label": "Intense Sourness", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_sourness/full-v2-sealed/sealed-selected", "mission": "emotion_sourness", "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": 6.267277727127075, "genuineness": 4.055205500125885, "wer": 0.015175840050283877, "identity": 0.6168031903356314, "voiceclap": -0.10178123071789741, "fitness": 0.6281485651772685, "steering_v2": 0.619928936779317, "raw_target": 0.4948654558509588, "target_cdf": 0.619928936779317, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 0.99, "by_arm": { "reference": { "n": 50, "ce": 6.2605562591552735, "genuineness": 4.0167804527282716, "wer": 0.0230919831121444, "identity": 0.6168031903356314, "fitness": 0.6271281690865321, "steering_v2": 0.626729958611394 }, "none": { "n": 50, "ce": 6.273999195098877, "genuineness": 4.093630547523499, "wer": 0.0072596969884233505, "identity": null, "fitness": 0.6291689612680049, "steering_v2": 0.6131279149472401 } } } } ], "selected_wording": { "id": "manual-909f760b761b", "general": "Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.", "inline": [ "Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.", "Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.", "Finish the utterance with a sudden, abrupt cessation of vocal energy." ], "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": 1.25 }, "n": 20, "target_z": -0.29326171980681526, "target_raw": 0.08830704428255558, "ce": 6.181467056274414, "genuineness": 4.332245588302612, "identity": 0.5525018602609635, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03377123475074768, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": -0.17509765198908256, "target_raw": 0.1393970761448145, "ce": 6.072453832626342, "genuineness": 4.216452705860138, "identity": 0.5365803048014641, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.04969279021024704, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -0.29326171980681526, "target_raw": 0.08830704428255558, "ce": 6.181467056274414, "genuineness": 4.332245588302612, "identity": 0.5525018602609635, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03377123475074768, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 0.739648408380365, "target_raw": 0.5349014475941658, "ce": 5.796247482299805, "genuineness": 3.914732003211975, "identity": 0.4237561909481883, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.16251690406352282, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 0.4465820158151126, "target_raw": 0.40818973556160926, "ce": 5.86038453578949, "genuineness": 3.937011981010437, "identity": 0.4756411023437977, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.11063199266791343, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.018749992676337764, "target_raw": 0.20699636451900005, "ce": 5.983098769187928, "genuineness": 4.128901851177216, "identity": 0.4714373849332333, "wer": 0.009298245614035087, "valid_fraction": 1, "identity_delta": -0.11483571007847786, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": -0.26328125210016784, "target_raw": 0.10126955546438694, "ce": 6.107401633262635, "genuineness": 4.2826648354530334, "identity": 0.5298515141010285, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.05642158091068268, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": -0.28876953186254894, "target_raw": 0.09024931006133556, "ce": 6.100848913192749, "genuineness": 4.270426607131958, "identity": 0.4938046082854271, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.09246848672628402, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -0.3460937532848779, "target_raw": 0.06546431109309196, "ce": 6.137980937957764, "genuineness": 4.296472120285034, "identity": 0.5179133005440235, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.06835979446768761, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.36025390516625955, "target_raw": 0.059341954067349434, "ce": 6.185041236877441, "genuineness": 4.303689622879029, "identity": 0.5197028867900372, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.06657020822167396, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": -0.17509765198908256, "target_raw": 0.1393970761448145, "ce": 6.072453832626342, "genuineness": 4.216452705860138, "identity": 0.5365803048014641, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.04969279021024704, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -0.27587891184371627, "target_raw": 0.09582276567816735, "ce": 6.118719959259034, "genuineness": 4.3030620336532595, "identity": 0.541227039694786, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.04504605531692505, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": -0.2814453147482566, "target_raw": 0.09341604672372342, "ce": 6.127059721946717, "genuineness": 4.24626384973526, "identity": 0.5450092777609825, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.041263817250728606, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -0.29707031453285476, "target_raw": 0.08666034042835236, "ce": 6.165978860855103, "genuineness": 4.296158361434936, "identity": 0.56335189640522, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.02292119860649109, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.32978515338919445, "target_raw": 0.07251558229327201, "ce": 6.190204000473022, "genuineness": 4.293961763381958, "identity": 0.5621646508574486, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.024108444154262543, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.33427734305667534, "target_raw": 0.07057331576943397, "ce": 6.1485049486160275, "genuineness": 4.378060674667358, "identity": 0.5630845293402672, "wer": 0.0058823529411764705, "valid_fraction": 1, "identity_delta": -0.02318856567144394, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.35273437459612156, "target_raw": 0.06259313747286796, "ce": 6.160816073417664, "genuineness": 4.295844554901123, "identity": 0.563905444741249, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": -0.022367650270462038, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.3678710989263752, "target_raw": 0.056048544496297835, "ce": 6.150490641593933, "genuineness": 4.3096518278121945, "identity": 0.5812122821807861, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.005060812830924988, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 1.1629882487445176, "target_raw": 0.7179388660937548, "ce": 5.70957317352295, "genuineness": 3.8671910166740417, "identity": 0.473368888348341, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": -0.11290420666337013, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 1.0460937463920195, "target_raw": 0.6673977501690388, "ce": 5.745910811424255, "genuineness": 3.805842709541321, "identity": 0.4395608399063349, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": -0.14671225510537625, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 0.9116210967723569, "target_raw": 0.6092564549297095, "ce": 5.707091021537781, "genuineness": 3.7639501690864563, "identity": 0.43489929400384425, "wer": 0.011867690058479532, "valid_fraction": 1, "identity_delta": -0.15137380100786685, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 0.7797851516659798, "target_raw": 0.5522551789879799, "ce": 5.882028293609619, "genuineness": 3.9142613768577577, "identity": 0.43776482343673706, "wer": 0.007894736842105263, "valid_fraction": 1, "identity_delta": -0.14850827157497407, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 0.6373046856825471, "target_raw": 0.4906515825539827, "ce": 5.914791822433472, "genuineness": 4.023621308803558, "identity": 0.5081921380013228, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.07808095701038838, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 0.29833986018112085, "target_raw": 0.34409498497843743, "ce": 5.972971892356872, "genuineness": 4.1196447849273685, "identity": 0.5097449950873851, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": -0.07652809992432594, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 0.18652345426095496, "target_raw": 0.29574946127831936, "ce": 5.973964691162109, "genuineness": 4.105366730690003, "identity": 0.4332985758781433, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.1529745191335678, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 0.18369139838110185, "target_raw": 0.29452497884631157, "ce": 6.0565684795379635, "genuineness": 4.145690298080444, "identity": 0.4637839823961258, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.12248911261558533, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 0.14736327739296096, "target_raw": 0.27881796322762964, "ce": 5.985481595993042, "genuineness": 4.141454017162323, "identity": 0.474043283611536, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.1122298114001751, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": -0.12236328342421224, "target_raw": 0.16219758242368698, "ce": 6.0649083137512205, "genuineness": 4.21535439491272, "identity": 0.5325976740568876, "wer": 0.007894736842105263, "valid_fraction": 1, "identity_delta": -0.05367542095482349, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": -0.15732421280625575, "target_raw": 0.14708169288933276, "ce": 6.116337132453919, "genuineness": 4.217080235481262, "identity": 0.5060836181044579, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": -0.08018947690725327, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": -0.1739257790084747, "target_raw": 0.13990375325083731, "ce": 6.0651068687438965, "genuineness": 4.218963074684143, "identity": 0.5309888493269682, "wer": 0.005902777777777778, "valid_fraction": 1, "identity_delta": -0.055284245684742925, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.2259765672792281, "target_raw": 0.11739880330860615, "ce": 6.172332978248596, "genuineness": 4.316869306564331, "identity": 0.5193063318729401, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": -0.06696676313877106, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": -0.24726562885030773, "target_raw": 0.10819415375590324, "ce": 6.058355617523193, "genuineness": 4.2233562707901005, "identity": 0.47705656960606574, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.10921652540564537, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -0.31533203175484803, "target_raw": 0.07876460924744606, "ce": 6.114351463317871, "genuineness": 4.247205317020416, "identity": 0.5066160053014755, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.07965708971023559, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.3549804728762913, "target_raw": 0.061622002720832826, "ce": 6.173524355888366, "genuineness": 4.297727406024933, "identity": 0.5199817188084126, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.06629137620329857, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.36396484359517994, "target_raw": 0.05773747339844704, "ce": 6.160418963432312, "genuineness": 4.405361425876618, "identity": 0.5862730950117111, "wer": 0.0027777777777777775, "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": -0.33447265995895026, "target_raw": 0.07048886753618717, "ce": 6.166375970840454, "genuineness": 4.384964370727539, "identity": 0.5486149296164513, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.03765816539525986, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.3082031229267574, "target_raw": 0.0818469014018774, "ce": 6.159227561950684, "genuineness": 4.418227291107177, "identity": 0.5948340922594071, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.008560997247695924, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.30488281227113556, "target_raw": 0.0832824882119894, "ce": 6.179084253311157, "genuineness": 4.343542492389679, "identity": 0.5317154571413993, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.05455763787031174, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.2901562480075331, "target_raw": 0.08964974224567414, "ce": 6.242149085998535, "genuineness": 4.378311710357666, "identity": 0.6032080364227295, "wer": 0.01239462292093871, "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": -0.28597656503904906, "target_raw": 0.09145689174532891, "ce": 6.236112642288208, "genuineness": 4.296221151351928, "identity": 0.5841147097945213, "wer": 0.011096837944664031, "valid_fraction": 1, "identity_delta": -0.01909332662820816, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 0.06460937308830876, "target_raw": 0.2430380541086197, "ce": 6.174874639511108, "genuineness": 4.208607630729675, "identity": 0.5608653366565705, "wer": 0.008484848484848484, "valid_fraction": 1, "identity_delta": -0.04234269976615906, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": -0.011601560860253556, "target_raw": 0.21008709773421289, "ce": 6.198464374542237, "genuineness": 4.225427384376526, "identity": 0.5334365478157997, "wer": 0.00823640127987954, "valid_fraction": 1, "identity_delta": -0.06977148860692978, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.0762109339485623, "ci95_z": [ 0.01593749149162768, 0.15835937627625585 ], "language_deltas": { "en": 0.04726562540387843, "de": 0.021093729159872877, "fr": 0.08515625145396234, "nl": 0.2324218768578408, "es": -0.004882813132742886 }, "languages_improved": 4, "clear_gain": true, "delta_ce": -0.02358973503112793, "delta_genuineness": -0.016819753646850587, "delta_wer": 0.000248447204968944, "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": 0.35058593812735783, "ci95_z": [ 0.19316405989094534, 0.5053906289795489 ], "language_deltas": { "en": 0.1390624964458698, "de": 0.4804687474690285, "fr": 0.5269531397281002, "nl": 0.49628905898625764, "es": 0.11015624800753307 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.06123800277709961, "delta_genuineness": -0.08761352062225342, "delta_wer": -0.0026119894598155466, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.0041796829684839915, "ci95_z": [ -0.02390625222940894, 0.025742184067033325 ], "language_deltas": { "en": 0.027734379765765503, "de": 0.009960928520436192, "fr": 0.03164061614159971, "nl": -0.049414065663714375, "es": 0.0009765560783329324 }, "languages_improved": 4, "clear_gain": false, "delta_ce": -0.0060364437103271485, "delta_genuineness": -0.0820905590057373, "delta_wer": -0.0012977849762746787, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 1.25, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793025216.0690002, "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. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 0.0, "cfg": 1.25, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "002deff97817deeea1d677e01a76c2fa11bf125a0b71ef21673af53f8f88ae2e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8efbd1d6cb36342b3c1d889a05e48ce26b0edb4b1e7f7f4fec7ed5587e02a958", "generation_seconds_batch": 15.678792178980075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21848106384277344, "target_z": 0.007812503769532035, "ce": 5.816103935241699, "genuineness": 4.093128204345703, "identity": 0.7233140468597412, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/002deff97817deeea1d677e01a76c2fa11bf125a0b71ef21673af53f8f88ae2e.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "0142b423bc14abd6db55d92f9627985921d59f4f43bac7b5194dee9a0d8b7e2f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "72867954ee1ca8602d975b631c43db1db97e7443a23295021a7a52500ab66dcb", "generation_seconds_batch": 23.030938738025725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.024724364280700684, "target_z": -0.5546874919224314, "ce": 6.316492557525635, "genuineness": 4.193545341491699, "identity": 0.3900344669818878, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0142b423bc14abd6db55d92f9627985921d59f4f43bac7b5194dee9a0d8b7e2f.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "017c41b9ccac9cbf590d4e16385c235f4968667219f4255446a3fbcaf59b9258", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "147aceff99c98f21c44c9547b9fc5e5b06946e2aa2e192cada476c219e2b4ec4", "generation_seconds_batch": 24.135054055950604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08167800307273865, "target_z": -0.30859376103934383, "ce": 6.205295085906982, "genuineness": 4.256305694580078, "identity": 0.6798586845397949, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/017c41b9ccac9cbf590d4e16385c235f4968667219f4255446a3fbcaf59b9258.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "01a38cff9c9510bc55e797519bafef3172167bf717a6d84a1f21a90e0df2dae0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e720ace0c3bbfbc1b7ec15c986651db8d3650835462f51c92837e273d7d763d", "generation_seconds_batch": 23.22317368199583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009054169058799744, "target_z": -0.4765624886914039, "ce": 6.24500846862793, "genuineness": 4.030367851257324, "identity": 0.5101728439331055, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/01a38cff9c9510bc55e797519bafef3172167bf717a6d84a1f21a90e0df2dae0.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "01f27885af7b884964dcc1c0f349373abc256b86fc79bc57346b9f0ed8f9601f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f7fbf39b858249e4440cc876db1555151134ef6f6602f1d90780c120ca25fca2", "generation_seconds_batch": 16.676183170988224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022565573453903198, "target_z": -0.44531250807756867, "ce": 5.9431867599487305, "genuineness": 4.024092197418213, "identity": 0.4211101531982422, "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_Sourness/01f27885af7b884964dcc1c0f349373abc256b86fc79bc57346b9f0ed8f9601f.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "3a4ca5e66c9267122d5de75fe6175bc81b6b43a65c16c8336ea4072a3a6c2c2f", "generation_seconds_batch": 17.673414538032375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03607699275016785, "target_z": -0.4140624929994405, "ce": 6.117925643920898, "genuineness": 4.457139015197754, "identity": 0.7839196920394897, "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_Sourness/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.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": "02172278fffd9f4a69b0f26efffb446fb6ab59c1e436c2095bbfc1ce3e5c14b5", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ca840a538ed1c380013ddf272738786b91ffbf3f1e64cdae79e478a89d4e4b6", "generation_seconds_batch": 24.431412128033116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15007953345775604, "target_z": -0.1503906286349059, "ce": 6.1894097328186035, "genuineness": 4.645420074462891, "identity": 0.7388606667518616, "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_Sourness/02172278fffd9f4a69b0f26efffb446fb6ab59c1e436c2095bbfc1ce3e5c14b5.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "0259b9d53ffdac6ad626d48bea31d69d7d11adf267876b9f1bb6bb1c302b1a79", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "05d4e6c11ef5aeadd3244bdde9bdeb69b636164f50a5690380638960514d2f91", "generation_seconds_batch": 28.18473938596435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03776592016220093, "target_z": -0.41015624111467447, "ce": 6.133810997009277, "genuineness": 4.632867813110352, "identity": 0.6837969422340393, "hypothesis": "J'ai trouvé la 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_Sourness/0259b9d53ffdac6ad626d48bea31d69d7d11adf267876b9f1bb6bb1c302b1a79.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "025c01765abbfcd2122c5c9b1c4c4a891d600063726c1882951d1c6f68deaf1f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d0b284ec74ea71901fe3f04773d6d0ea1788b3409d06cd0f4a835ce7970fe30c", "generation_seconds_batch": 19.37358506396413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08505585789680481, "target_z": -0.3007812572698118, "ce": 5.871703147888184, "genuineness": 3.9801597595214844, "identity": 0.20500653982162476, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/025c01765abbfcd2122c5c9b1c4c4a891d600063726c1882951d1c6f68deaf1f.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "029a90f702ab5b9000dafa6d905bfda5e7bb5ccb85a6b36de23841c98952f918", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e29bdc338cac6793e451e5ed42a9645bb24c8d0fb248c7e0c5aaad64e0785c75", "generation_seconds_batch": 23.87824733799789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010743096470832825, "target_z": -0.4726562368066379, "ce": 6.006728172302246, "genuineness": 4.344170093536377, "identity": 0.5014782547950745, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/029a90f702ab5b9000dafa6d905bfda5e7bb5ccb85a6b36de23841c98952f918.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "02e685741f0566597a372796889b57b070d0c944533ba2ca8afed512439e080a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4f7f49ca43c8071cd3ed88e0a44e5783df0e5d48fcd8d664fb85f55702790e71", "generation_seconds_batch": 24.62609562498983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07492230832576752, "target_z": -0.324218734114115, "ce": 6.149696350097656, "genuineness": 3.936227321624756, "identity": 0.36033469438552856, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/02e685741f0566597a372796889b57b070d0c944533ba2ca8afed512439e080a.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "03003ab5bab223a0b76eed9706dd835c52005201259eabb026cd086740654e65", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e4b74daab88f361640b5deb24da0761cf1dfe8a1d0f96f0a4c5bfe725ec7b164", "generation_seconds_batch": 24.548798877047375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03861038386821747, "target_z": -0.40820311517229146, "ce": 6.268836498260498, "genuineness": 4.406930446624756, "identity": 0.2567288875579834, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/03003ab5bab223a0b76eed9706dd835c52005201259eabb026cd086740654e65.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": "0357d073723c152b401f3741e3ca32f3780e486c8200a2d87c7fd68938f7782b", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d7665b3f9581b1961ac7e17136568b1384bf11da8c5fa14d12e08a710d2a8d31", "generation_seconds_batch": 14.483398671029136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05972196161746979, "target_z": -0.35937500107700915, "ce": 6.205295085906982, "genuineness": 4.419482707977295, "identity": 0.2980353832244873, "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_Sourness/0357d073723c152b401f3741e3ca32f3780e486c8200a2d87c7fd68938f7782b.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "03ff126681df057f3d57d1014793b09df3115e541b9e0a59b0f573a625b64d2e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "30884cad015b70e3c94698a66fc89856c5ffcf968620aeabc45becb022b35fec", "generation_seconds_batch": 17.03485972993076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.024724364280700684, "target_z": -0.5546874919224314, "ce": 5.919358730316162, "genuineness": 4.570107460021973, "identity": 0.4516453742980957, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/03ff126681df057f3d57d1014793b09df3115e541b9e0a59b0f573a625b64d2e.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": "04524a7e7755d6d7f6275bb8bc93579ab4f2ab5d2062bfc84ecca2c8aa330dd3", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "401a25b30202b03d352aa5746509b52e3f710e5a77c83974f6c13937ff60c506", "generation_seconds_batch": 19.70577400701586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08167800307273865, "target_z": -0.30859376103934383, "ce": 6.292664527893066, "genuineness": 4.118232727050781, "identity": 0.6943809986114502, "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_Sourness/04524a7e7755d6d7f6275bb8bc93579ab4f2ab5d2062bfc84ecca2c8aa330dd3.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "04999227a5a206e58efc127771aef9377fe51edbd2024d16a3ac8c3891e4353f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "089dce92537617daa383cf0f56bbf36da471bcdf7793f333fd6455ec2b22178e", "generation_seconds_batch": 24.19409443391487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00314292311668396, "target_z": -0.490234370288085, "ce": 6.1020402908325195, "genuineness": 4.607763767242432, "identity": 0.5702126026153564, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/04999227a5a206e58efc127771aef9377fe51edbd2024d16a3ac8c3891e4353f.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "04c4bec92415486146eb2e11edec5e68fac91dd29678ce70170f9190c5713a4e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "711f1573dbec75d70b1d2bbd40584e8dc60091b813d1c03dd88c731365b0263e", "generation_seconds_batch": 23.00159340305254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10870083421468735, "target_z": -0.246093748115234, "ce": 6.117925643920898, "genuineness": 4.068024158477783, "identity": 0.5800114870071411, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/04c4bec92415486146eb2e11edec5e68fac91dd29678ce70170f9190c5713a4e.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "04c7757e87598e9b29394e59128e555788a5589194cc3219d8f94f0148da01e3", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e8633c7d294872e3155b850759dd7f8bbc030ce67333ed53e1b2291d5c9fc943", "generation_seconds_batch": 24.25011874199845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1036340519785881, "target_z": -0.257812503769532, "ce": 6.1020402908325195, "genuineness": 4.105680465698242, "identity": 0.42469310760498047, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/04c7757e87598e9b29394e59128e555788a5589194cc3219d8f94f0148da01e3.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "05426d282ac1ec0a47f25473cbfd2e3a650b1f98d3051979ab003e2c0cb562b7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8b9e2e08ee6966c8e63a0af8dce267416df020e4547cc9715ee0317a913f32d0", "generation_seconds_batch": 23.10034234903287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2823493480682373, "target_z": 4.781249963381689, "ce": 5.689021587371826, "genuineness": 3.537698984146118, "identity": 0.4779638648033142, "hypothesis": "De deur 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_Sourness/05426d282ac1ec0a47f25473cbfd2e3a650b1f98d3051979ab003e2c0cb562b7.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "05458c6731cca36742e03d171fbd2527a90a4479b73a35b3b868a81e6dfb8d08", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ea24b73bf0a5286ba6299a398fa0bb2347f0ba8d0688a077b84fc6827ed1117a", "generation_seconds_batch": 22.163581931963563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09181156754493713, "target_z": -0.2851562497307477, "ce": 5.871703147888184, "genuineness": 3.5690791606903076, "identity": 0.35234034061431885, "hypothesis": "I found the little box. It was beside the OO window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/05458c6731cca36742e03d171fbd2527a90a4479b73a35b3b868a81e6dfb8d08.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "989d073215f540a5b37eee866cb12d9fc7d4330feab07011f781909e6467a6a7", "generation_seconds_batch": 18.595297037041746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07154445350170135, "target_z": -0.332031237883647, "ce": 6.316492557525635, "genuineness": 4.846253395080566, "identity": 0.5932444334030151, "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_Sourness/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.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": "05ad5055e869a6f831ad65d29535dc6f0ea65cb269f0e5b8df0b40a6b90a9a44", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d911daa8b9c969664b2c23bfd118b9b031da4a3f6cd901e9e0c0ddfdb0d50cd", "generation_seconds_batch": 16.21318983391393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16950219869613647, "target_z": -0.10546873196009669, "ce": 6.24500846862793, "genuineness": 4.105680465698242, "identity": 0.5640962719917297, "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_Sourness/05ad5055e869a6f831ad65d29535dc6f0ea65cb269f0e5b8df0b40a6b90a9a44.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "063031908da760254e633d241af36aef50c22f091c55f9430565fd1ec73cdf5e", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "33e9b3a85624d155eb0b6b8a1416919db73049933c9ce1275e51424d5afa5439", "generation_seconds_batch": 16.85071189503651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07154445350170135, "target_z": -0.332031237883647, "ce": 6.0146708488464355, "genuineness": 4.570107460021973, "identity": 0.6148666143417358, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/063031908da760254e633d241af36aef50c22f091c55f9430565fd1ec73cdf5e.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "0651b28ac287edad4d2ab8e0023fdaaee7e2e417c02fc6969a5b16dcff6e0997", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f7ad25a44e98a86d32f69d38d8a076a8a4bc47da04d939510a876d205a005ffb", "generation_seconds_batch": 27.76792336406652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00023493170738220215, "target_z": -0.498046874057617, "ce": 5.959072113037109, "genuineness": 4.030367851257324, "identity": 0.5780178308486938, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0651b28ac287edad4d2ab8e0023fdaaee7e2e417c02fc6969a5b16dcff6e0997.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "06b4fce8e426b2a1d4f45001a81d556264978bcdb95c0e7178ed5df3050c1acd", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e1a73e099f1cb0639d7c3357b50dcdcee1b093a64fbc1eb70a45f6d477f5581a", "generation_seconds_batch": 26.27216082101222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012432023882865906, "target_z": -0.46874998492187187, "ce": 6.157639026641846, "genuineness": 4.20609712600708, "identity": 0.36467885971069336, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/06b4fce8e426b2a1d4f45001a81d556264978bcdb95c0e7178ed5df3050c1acd.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "06f215c609383fb1c7da6aa470b4e24355cc3398cface0778fabe8a5306922eb", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "af09b0331ec20847f955bd79e138186e366df4eae7ac7533dd98d6ea57c67906", "generation_seconds_batch": 24.720328395953402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2892606258392334, "target_z": 2.484375233710986, "ce": 6.054384231567383, "genuineness": 3.625563621520996, "identity": 0.7192018032073975, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/06f215c609383fb1c7da6aa470b4e24355cc3398cface0778fabe8a5306922eb.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "07403d979c8d4f639c9def08237a1d5957b07680a8c7b854673884f5b0867cce", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e3cdfa110fda3ffb23be002b17ff24d627188b4f99ace20218b26809d87e0140", "generation_seconds_batch": 24.54062028496992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019187718629837036, "target_z": -0.4531250118471007, "ce": 6.1020402908325195, "genuineness": 4.306513786315918, "identity": 0.3695325255393982, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/07403d979c8d4f639c9def08237a1d5957b07680a8c7b854673884f5b0867cce.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "078b60e781e9e14472e8b1c023a1806d1005356f14926a718d0a1b1cf9a40ab6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19c8ba570d938d567a175541f27194f550289c0d96ac1ad0783aaf56b626ee56", "generation_seconds_batch": 18.947562271961942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012432023882865906, "target_z": -0.46874998492187187, "ce": 6.086154937744141, "genuineness": 4.055472373962402, "identity": 0.17203465104103088, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/078b60e781e9e14472e8b1c023a1806d1005356f14926a718d0a1b1cf9a40ab6.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "07a42b7bb8fc19acd2a4f01a94b54bae8d6ff3f712bef57755f436d594d236a1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2326383e94ac8966481bf3f17893447fa73d7f1cf4cb9cc3a05bcb4922ba7645", "generation_seconds_batch": 25.17687969096005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15092399716377258, "target_z": -0.14843750269252287, "ce": 6.181467056274414, "genuineness": 4.017816066741943, "identity": 0.4743197560310364, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/07a42b7bb8fc19acd2a4f01a94b54bae8d6ff3f712bef57755f436d594d236a1.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "07e83b32c8bbf6930b3f1d9f711241168ae8a163ac4d3b22cc6d783c33290f6e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "542aaa74de36aa5f33e28971e4f75785e9bf2b8abbb3910262302ada63688bc6", "generation_seconds_batch": 24.143614604021423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07154445350170135, "target_z": -0.332031237883647, "ce": 6.078212261199951, "genuineness": 3.9048471450805664, "identity": 0.3465038537979126, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/07e83b32c8bbf6930b3f1d9f711241168ae8a163ac4d3b22cc6d783c33290f6e.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "07f68f2b0c891f7a25d78f66b93dcf83a4aeccb1b0b3b1a3e1bc005e215f19cb", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e25644e25c2196e4aebbd10a4b4481ad0b23601dfa5df23b280dbdee64c3deb7", "generation_seconds_batch": 23.512240311014466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.024724364280700684, "target_z": -0.5546874919224314, "ce": 6.332377910614014, "genuineness": 4.268857479095459, "identity": 0.5257071852684021, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/07f68f2b0c891f7a25d78f66b93dcf83a4aeccb1b0b3b1a3e1bc005e215f19cb.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "082aa2d7452cce654c2a0a63a27cca5fec36e8b331a9f15392d3f40684a1f4fa", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "30d7c1af3d56416b5c0a5d1a3905a21ab6a8f0317c9219bfb07a0bb0551091a1", "generation_seconds_batch": 18.256609981996007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.41180419921875, "genuineness": 4.18099308013916, "identity": 0.326296865940094, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/082aa2d7452cce654c2a0a63a27cca5fec36e8b331a9f15392d3f40684a1f4fa.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "0889a5f1e5dc4d1a630b62fb289b94ac9df0ee4a2d6c483b39641697192d42ea", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "aebfd6ed56bf80636a1eda673d16a9b97c9d499d2881d8b90eeed3d78257a942", "generation_seconds_batch": 25.43275898799766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031010210514068604, "target_z": -0.42578124865373856, "ce": 6.1894097328186035, "genuineness": 4.086852550506592, "identity": 0.3686509132385254, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0889a5f1e5dc4d1a630b62fb289b94ac9df0ee4a2d6c483b39641697192d42ea.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "08921240d08c04b8b9600e9ce2406653cca7a193e2b7cf491dd9cda1aa540ddb", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "90831713f5ea378a79a08fd8f828caeb1eda36bafb427feaa6cf7c2768386539", "generation_seconds_batch": 16.990537362988107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20665857195854187, "target_z": -0.019531259423830088, "ce": 5.8875885009765625, "genuineness": 3.6287014484405518, "identity": 0.581161379814148, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/08921240d08c04b8b9600e9ce2406653cca7a193e2b7cf491dd9cda1aa540ddb.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "08b17115f3fa9a57ba45ee68d895d2963953a27523cad6b7e9bd77e2ed734764", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "973d2bb65fc7506c5acb3a40d192dbf9b8d0b681a7c8dd079ce562113efafe3c", "generation_seconds_batch": 24.44486677297391, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12390117347240448, "target_z": -0.21093749838448628, "ce": 6.046441555023193, "genuineness": 4.13078498840332, "identity": 0.6730775833129883, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/08b17115f3fa9a57ba45ee68d895d2963953a27523cad6b7e9bd77e2ed734764.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": "08c304f04869de1fa366ee12e0e8b319aad718bce91e362c8f8b6f6f3f40bcaa", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I wrote the number on the envelope.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a30c6dc3b0a12887b234507887c3b61c15d8fb011f8326944a75bf4c246a1645", "generation_seconds_batch": 15.531335202045739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10870083421468735, "target_z": -0.246093748115234, "ce": 6.23706579208374, "genuineness": 3.8295347690582275, "identity": 0.3653962314128876, "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_Sourness/08c304f04869de1fa366ee12e0e8b319aad718bce91e362c8f8b6f6f3f40bcaa.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "08d9da2f534e02a91b9e536842dbefb47f419d1f8be2cae260dc88a101a9ce33", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fb35d77d69fe76f9c894576aa4b410fa63f97270437dc8de96aaaf0e22d4b73d", "generation_seconds_batch": 24.261224566027522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9041852355003357, "target_z": 1.5937499418415058, "ce": 5.422942161560059, "genuineness": 3.8420867919921875, "identity": 0.42978084087371826, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/08d9da2f534e02a91b9e536842dbefb47f419d1f8be2cae260dc88a101a9ce33.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "0944da78f91af6098d2dd31d2d3d1cb12d8961664217820fd9420c315b8cb779", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "092fade715260e5a4c07962c663d1f5ce49bffa9bea1b70141cc7588d37cb9e3", "generation_seconds_batch": 25.051864368026145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13572365045547485, "target_z": -0.18359376965541704, "ce": 6.022613525390625, "genuineness": 4.256305694580078, "identity": 0.520844578742981, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0944da78f91af6098d2dd31d2d3d1cb12d8961664217820fd9420c315b8cb779.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "096524e9e0444fc7f368445560441797b7a014215ebd0e49fdec7e15768fcb1b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d5953876040d077d0b1f79ccb7944ac275f187282129349d10e969c89d16b04f", "generation_seconds_batch": 26.917664909968153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03945484757423401, "target_z": -0.40624998922990846, "ce": 5.982900142669678, "genuineness": 4.532451152801514, "identity": 0.7009392976760864, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/096524e9e0444fc7f368445560441797b7a014215ebd0e49fdec7e15768fcb1b.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "0987109968b22b72fd54345a41a101ee466eeefae3c48dcc6bc7bd587ec25951", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bebe405dcc479f63caf7dd3ed7f3eace33f4d15edb6b6f7f29913c53776e7d4e", "generation_seconds_batch": 23.385917713982053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18808038532733917, "target_z": -0.06249999569196339, "ce": 5.839932441711426, "genuineness": 3.7918784618377686, "identity": 0.8030192852020264, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0987109968b22b72fd54345a41a101ee466eeefae3c48dcc6bc7bd587ec25951.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "09ff2375f611700b94a91ccea04a5255a25f5356bce4e30c2cea08a9b05e79bd", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "84154d52bf2ff922746fb6f486d958232a2245c36e5824f3439da84caca5cd41", "generation_seconds_batch": 16.064682033029385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014590814709663391, "target_z": -0.5312500150781282, "ce": 6.2767791748046875, "genuineness": 4.457139015197754, "identity": 0.6098920702934265, "hypothesis": "J'ai trouvé la 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_Sourness/09ff2375f611700b94a91ccea04a5255a25f5356bce4e30c2cea08a9b05e79bd.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": "0ad31a96d640f750736e3689f711116768354c2cd993e672a2126dd6dcd4b316", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2686b7ce401f1d32a51909441aea19128e25c31e5ed02836572d5a1c015c2e7", "generation_seconds_batch": 18.753390555037186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08421139419078827, "target_z": -0.3027343832121948, "ce": 6.213237762451172, "genuineness": 4.394378662109375, "identity": 0.5989568829536438, "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_Sourness/0ad31a96d640f750736e3689f711116768354c2cd993e672a2126dd6dcd4b316.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "0b58f33e99abb11924b300a288f435404432dafdc0a6f2be4e748afdcead3d58", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1361669817b2707914e1b2b512c33e638f9b730bab602d6ac01156cbc3bfc1a6", "generation_seconds_batch": 23.800385601934977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030165746808052063, "target_z": -0.42773437459612157, "ce": 6.078212261199951, "genuineness": 4.469690799713135, "identity": 0.6088573932647705, "hypothesis": "J'ai trouvé la 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_Sourness/0b58f33e99abb11924b300a288f435404432dafdc0a6f2be4e748afdcead3d58.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "0ba5c61a3a5b2f81357d4db35a1580c438a8586793b409f6c4d0326da2cae511", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3183756d5a23c7f9af30beec21c53b1076fd0d1f36eb19cf056871a24af471c2", "generation_seconds_batch": 21.737091127899475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08505585789680481, "target_z": -0.3007812572698118, "ce": 6.292664527893066, "genuineness": 4.432034492492676, "identity": 0.49895796179771423, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0ba5c61a3a5b2f81357d4db35a1580c438a8586793b409f6c4d0326da2cae511.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "0c0dc08c82593bd998dfe58b69f230ed32a8c86f4186432e40656f9b33820d1d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "80715cb714f615de69c4dbda9c0fe5f67df44165f780db462eac69c8672be107", "generation_seconds_batch": 23.87824733799789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007835105061531067, "target_z": -0.515625007539064, "ce": 6.117925643920898, "genuineness": 4.168440818786621, "identity": 0.19778844714164734, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0c0dc08c82593bd998dfe58b69f230ed32a8c86f4186432e40656f9b33820d1d.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": "0c932eef930a5376b21f3643cdf561af7990c293a821640b864c2542181e81c9", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "09cebbc97553b8ce178f8af815ac461b71461f1fc8beb1188b1797840a3d4a55", "generation_seconds_batch": 23.93971678800881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015809863805770874, "target_z": -0.4609375156166327, "ce": 6.054384231567383, "genuineness": 4.287685871124268, "identity": 0.5385535955429077, "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_Sourness/0c932eef930a5376b21f3643cdf561af7990c293a821640b864c2542181e81c9.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "4e79e60c55b0e6c3acb49047118713c56dcf44af69bd32a8461c65b11ef6a1f2", "generation_seconds_batch": 17.13628765696194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 6.165581703186035, "genuineness": 4.319066047668457, "identity": 0.726905345916748, "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_Sourness/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.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": "0ce9d244a5a5216996242366489f24d88141c36d03022476face0e8f80b1e12a", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57041ecbfea4e281c860f1504cbbc5924ebc903755ef8d1618ff70d8a89afbaf", "generation_seconds_batch": 15.44909840496257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6677355766296387, "target_z": 1.046875091545778, "ce": 6.23706579208374, "genuineness": 4.356721878051758, "identity": 0.39295873045921326, "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_Sourness/0ce9d244a5a5216996242366489f24d88141c36d03022476face0e8f80b1e12a.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "0d08c3c1c0a03927360181884b8b772402fe5b0df6a21161d3e5ca659358be8c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a969b93aa6c72a329e8f73e99c39894a5b79976add186e0dd61ba6321fbe2fc6", "generation_seconds_batch": 25.44204349606298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011212959885597229, "target_z": -0.5234375113085961, "ce": 6.284721851348877, "genuineness": 4.6705241203308105, "identity": 0.5904026031494141, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0d08c3c1c0a03927360181884b8b772402fe5b0df6a21161d3e5ca659358be8c.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "0d0feeb454c4bd0129403396b7d5100c0f10742bc7e36ef41fea52eca3ddcab1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2e9783ab690fc0ae54d1b96c61652abea9f1873c18a695eeb1f52766df1494fa", "generation_seconds_batch": 24.028510999050923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16274648904800415, "target_z": -0.12109373949916076, "ce": 6.006728172302246, "genuineness": 4.13078498840332, "identity": 0.577326774597168, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0d0feeb454c4bd0129403396b7d5100c0f10742bc7e36ef41fea52eca3ddcab1.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": "0d9cec57d1e9afee1dba0df1e9311e1b8a39ec01dd1a2b0a5f90bf32eef9bb4a", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e70bfa173de958a473ead19fb5839380c4b53e5c7c4e9a40ae00ebb67a0d2ca5", "generation_seconds_batch": 27.20446896390058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4380415081977844, "target_z": 0.5156249730747712, "ce": 5.788304805755615, "genuineness": 3.948779582977295, "identity": 0.6469300985336304, "hypothesis": "De vech gaat linksaf naar de brug. Loop 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_Sourness/0d9cec57d1e9afee1dba0df1e9311e1b8a39ec01dd1a2b0a5f90bf32eef9bb4a.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "0da20d53e7b120bc9522bfbccd297f126eb37e826da60956524e8f4b829e45c8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6043f6ebfefaedb379ecade6626ac3f451d717caa7c7d0eb0b10aa1e4900fd4f", "generation_seconds_batch": 16.347756145056337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05803303420543671, "target_z": -0.36328125296177516, "ce": 5.7128496170043945, "genuineness": 3.8797430992126465, "identity": 0.5254799127578735, "hypothesis": "La puerta sigue abierta y 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_Sourness/0da20d53e7b120bc9522bfbccd297f126eb37e826da60956524e8f4b829e45c8.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "0e0b06391c3e6edd70eada9dd5cf4638245b83e533d177e17b9dfa6f516e6220", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "abdba8d4ccc8a6da3c9b1a778894244e19ef3e3fe73240ca98a0fd93c916edbf", "generation_seconds_batch": 23.56518282799516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0495883971452713, "target_z": -0.38281251238560526, "ce": 5.871703147888184, "genuineness": 3.7040140628814697, "identity": 0.49810531735420227, "hypothesis": "I found little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0e0b06391c3e6edd70eada9dd5cf4638245b83e533d177e17b9dfa6f516e6220.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": "0e705c975a5b24679bbf5066ad735906126134738ac9bda54846c468f02a6666", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80176f628bfe9911af9c90965b1446bb0546f25a6dd826a5489ae067b7c4d294", "generation_seconds_batch": 18.382263578940183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10278958827257156, "target_z": -0.259765629711915, "ce": 6.23706579208374, "genuineness": 4.256305694580078, "identity": 0.642806887626648, "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_Sourness/0e705c975a5b24679bbf5066ad735906126134738ac9bda54846c468f02a6666.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "0e8ae711ed2bfbf2e0000f6f1a9936efb6fcd37c5a47f08075a684842e14cc0a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a7f6eff774a63835bc50c634cdff19af1de2e2d711a627ab9ef938fe74848337", "generation_seconds_batch": 24.31401565298438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4186188578605652, "target_z": 0.47070311086425487, "ce": 5.879645347595215, "genuineness": 4.017816066741943, "identity": 0.5665963888168335, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0e8ae711ed2bfbf2e0000f6f1a9936efb6fcd37c5a47f08075a684842e14cc0a.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "0ebaee5b15df92731f1843cc156a35660b4115985fdd4f37cda0d9f7f6464ba6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bec44ccde982563285e7bf5d4b2373bd45cbeb774e2aaee14148a54806a4049c", "generation_seconds_batch": 25.17687969096005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48870933055877686, "target_z": 0.6328125296177517, "ce": 6.149696350097656, "genuineness": 3.8295347690582275, "identity": 0.6071263551712036, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0ebaee5b15df92731f1843cc156a35660b4115985fdd4f37cda0d9f7f6464ba6.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "0ee9a73d5e78c2719b71767cf16324783d384088023470c68ed838e8e538f635", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4bb6bf0e3232b4372b88e3af22e19000598157b805cb7040cba60e4a207d1574", "generation_seconds_batch": 20.57722041301895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2283036708831787, "target_z": 4.656249903069177, "ce": 5.33954381942749, "genuineness": 3.4466962814331055, "identity": 0.4415736794471741, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je hier 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_Sourness/0ee9a73d5e78c2719b71767cf16324783d384088023470c68ed838e8e538f635.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": "0eedbe77a45472ab1f31fec5565bfc262c58a97a4fec6ec2b65b34cda1408a18", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Escribí el número en el sobre.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "848cb46704792d0e2f5e09b96a9dbc2948ed4ad848e4de4a08b0882dfe16b915", "generation_seconds_batch": 17.63024494610727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1036340519785881, "target_z": -0.257812503769532, "ce": 6.300607204437256, "genuineness": 4.607763767242432, "identity": 0.4429967403411865, "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_Sourness/0eedbe77a45472ab1f31fec5565bfc262c58a97a4fec6ec2b65b34cda1408a18.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "0f2e6876a3dc0e71c831ca2f40e330c199cb612e40d13ebfecb29add37acb972", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "aec57a1a0e74433a8f0fa765a6483e20544e2b6f72b358e10556326dd0fb20f4", "generation_seconds_batch": 22.915424890932627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06225535273551941, "target_z": -0.35351562324986013, "ce": 5.959072113037109, "genuineness": 4.406930446624756, "identity": 0.6042270064353943, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0f2e6876a3dc0e71c831ca2f40e330c199cb612e40d13ebfecb29add37acb972.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "0f452525f8b807a81c91095dd4fabb1afe23119175e2b5f0a423278459ea9649", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "16c04f63fadeb57ae1bfc56f1daf4df964f2ef08640e1d6397f8044ac7e70d87", "generation_seconds_batch": 24.502812259015627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04836934804916382, "target_z": -0.6093750183091556, "ce": 5.998785495758057, "genuineness": 4.124508857727051, "identity": 0.6530051231384277, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0f452525f8b807a81c91095dd4fabb1afe23119175e2b5f0a423278459ea9649.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "0f535997d8c0bbf22c93129ddee5aa8339ac7bc15559bf692711cf50d8fc862c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f0c6f9176f66afdaa286edc577945e0dd6b818273935227df7f10ee25bddfac", "generation_seconds_batch": 20.38611501606647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10194512456655502, "target_z": -0.26171875565429803, "ce": 6.23706579208374, "genuineness": 4.2249250411987305, "identity": 0.37132978439331055, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0f535997d8c0bbf22c93129ddee5aa8339ac7bc15559bf692711cf50d8fc862c.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "0f593600f9e41a8d9729aeb0d02cd82839a7cdb0828439bc5e32d512780cf94a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2596846c4361995090f288eea23a96f763d64a1256fa9ea5d85626ae36bf8bee", "generation_seconds_batch": 23.656512449029833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0453660786151886, "target_z": -0.3925781420975203, "ce": 5.808161735534668, "genuineness": 4.469690799713135, "identity": 0.6010279059410095, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/0f593600f9e41a8d9729aeb0d02cd82839a7cdb0828439bc5e32d512780cf94a.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "1026af010e0b5def2865a46d0f3d140ad6d338a13a9d46a4eed74ddfda74fe9f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7d3fce2c1536a9031a9fb0ca5ea776d8e92792f4b68a0e25c29abd7032678ea1", "generation_seconds_batch": 21.799316844902933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06478874385356903, "target_z": -0.3476562454227111, "ce": 5.919358730316162, "genuineness": 3.6789097785949707, "identity": 0.23148225247859955, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1026af010e0b5def2865a46d0f3d140ad6d338a13a9d46a4eed74ddfda74fe9f.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": "1056819c68d5401074c3d62cf494414c551fa00bab35c10b5ba8456a9cf8461f", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Escribí el número en el sobre.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "77813080b9b47b3d40174eeee54370453ddc036602b972b3c69a90eea63eee90", "generation_seconds_batch": 17.63024494610727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07154445350170135, "target_z": -0.332031237883647, "ce": 6.292664527893066, "genuineness": 4.444586753845215, "identity": 0.6854026317596436, "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_Sourness/1056819c68d5401074c3d62cf494414c551fa00bab35c10b5ba8456a9cf8461f.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "105822d64728bdee32c8f5fecdb93c779db4d21cbb68f6afca6793ae3608b60e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7a3d74bd5a85aae51285ae933b248008dff55800cb050ed68b02677d8e9f9f74", "generation_seconds_batch": 20.34817962499801, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14247936010360718, "target_z": -0.16796876211635298, "ce": 5.744620323181152, "genuineness": 3.9299514293670654, "identity": 0.6576964855194092, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/105822d64728bdee32c8f5fecdb93c779db4d21cbb68f6afca6793ae3608b60e.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "107b08dceb1ebf0b0566587ed09e37ec1843d096a0f7d4df1b74196f0f9ae981", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a8de4607cb87fc43ae2449269fe3828b3beb0e802450911bc3a06422948d3c65", "generation_seconds_batch": 30.301184987998568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42199671268463135, "target_z": 0.4785156146337869, "ce": 5.903473377227783, "genuineness": 4.005263805389404, "identity": 0.46230873465538025, "hypothesis": "De deur 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_Sourness/107b08dceb1ebf0b0566587ed09e37ec1843d096a0f7d4df1b74196f0f9ae981.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "107c056ae092159086df910d0b50fb39eff579624e916c25db390ac39b11ebaf", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b6a19e522165d504873081035c45463008fe4a90818c96378a5479a30e2b0c30", "generation_seconds_batch": 23.775772585067898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.125868320465088, "genuineness": 4.582659721374512, "identity": 0.7465537786483765, "hypothesis": "J'ai trouvé la 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_Sourness/107c056ae092159086df910d0b50fb39eff579624e916c25db390ac39b11ebaf.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "1091bf38f4aa5eb10078ffb3b621f4b5c52cee507eb91b4ecde441db6e4e2bb8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4ea0df013c29f6bd0afb64b57ca80e6f93e658387a7cec0c900d87049e7a908d", "generation_seconds_batch": 23.685977277928032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0006095319986343384, "target_z": -0.496093748115234, "ce": 6.260893821716309, "genuineness": 4.406930446624756, "identity": 0.4141817092895508, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1091bf38f4aa5eb10078ffb3b621f4b5c52cee507eb91b4ecde441db6e4e2bb8.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": "1158bc7ac4e0e2e82e09ab33eef2d587c53d60ac20d0b2217a9f165f3630c2ca", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3f0aa160ac547b1d3dc84fe969f153859cb7693bd67cde23b8e2f4c1822519a0", "generation_seconds_batch": 14.482412993093021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13741257786750793, "target_z": -0.17968751777065103, "ce": 6.006728172302246, "genuineness": 4.174716949462891, "identity": -0.09032310545444489, "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_Sourness/1158bc7ac4e0e2e82e09ab33eef2d587c53d60ac20d0b2217a9f165f3630c2ca.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "118fa613b27ebe7e909b5c3158ca30db383d9ead92e6c6803dc089e1a279efeb", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8d8885e93352cbbf93ad3d7985c2ee2210e8555a2e59a935718d0306fea51809", "generation_seconds_batch": 15.226851866929792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09181156754493713, "target_z": -0.2851562497307477, "ce": 6.078212261199951, "genuineness": 4.287685871124268, "identity": 0.7266453504562378, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/118fa613b27ebe7e909b5c3158ca30db383d9ead92e6c6803dc089e1a279efeb.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "11b99fa34439aa2602e956e2dbb83f06e7c31f36cb80102220d517a669fd497f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c81aced7d705023d63cb8a31483929c2e4d9e4d771250ae1e31d01811979d99e", "generation_seconds_batch": 23.918151834979653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09772281348705292, "target_z": -0.2714843681340667, "ce": 5.919358730316162, "genuineness": 4.268857479095459, "identity": 0.3588255047798157, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/11b99fa34439aa2602e956e2dbb83f06e7c31f36cb80102220d517a669fd497f.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "1238f4b3afca49df7b4b649e7dcbd71adc6d060c2c1d433dbb670240c0c1abd8", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bb8f65b651433e2b7fde41212e1b1c17c8b5a96071f4173c2359ed6208c167c6", "generation_seconds_batch": 18.256609981996007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.340320587158203, "genuineness": 4.306513786315918, "identity": 0.5362209677696228, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1238f4b3afca49df7b4b649e7dcbd71adc6d060c2c1d433dbb670240c0c1abd8.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "124c5f7e67bee1faabb8d2ab596118a3b0f182358682ba25a936cf5a31e02e3c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "69b8e885fb5b82810f51fa32af0c6654c9cc4f30ff75d821430dd9bea4c86b69", "generation_seconds_batch": 24.25011874199845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13403472304344177, "target_z": -0.18750002154018305, "ce": 6.09409761428833, "genuineness": 4.080576419830322, "identity": 0.4082164764404297, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/124c5f7e67bee1faabb8d2ab596118a3b0f182358682ba25a936cf5a31e02e3c.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "12576eef1f8bd9c42ab811abacd132068171356d9c37a6adf8f5335eb894cf45", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "92d3040a4e855c61a80d5d118d923d199e78f071b3675685a8d0310bc5e283a9", "generation_seconds_batch": 25.890148665988818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06647767126560211, "target_z": -0.3437499935379451, "ce": 5.967014789581299, "genuineness": 4.042920112609863, "identity": 0.3482629060745239, "hypothesis": "I f found the little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/12576eef1f8bd9c42ab811abacd132068171356d9c37a6adf8f5335eb894cf45.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "128c6a377439151ec4ef4cd2f5645add36d463a3b709217571bd47e23a28e52e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a9b3d9c8eaf7e3afd0fe51d9cf10468f3fe863779a8c10c2ee6b6aca86c72505", "generation_seconds_batch": 23.5877281910507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24381496012210846, "target_z": 0.0664062475767294, "ce": 5.744620323181152, "genuineness": 3.47493839263916, "identity": 0.371317058801651, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/128c6a377439151ec4ef4cd2f5645add36d463a3b709217571bd47e23a28e52e.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5545089056817449d159045b7cde789dc17d932cc1e681657a3daa1fbaaef79", "generation_seconds_batch": 17.866728006047197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08590032160282135, "target_z": -0.29882813132742875, "ce": 6.173524379730225, "genuineness": 4.356721878051758, "identity": 0.7298756837844849, "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_Sourness/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "12d75e09a5931c0d04fd3437773a070edac78d3ae9618fff12ed92753a5353c7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 128, "seconds_generated": 10.24, "mp3_sha256": "28aea14571af65f0c7af73bdb2b93d5699eb3c00457d621efd5ff0702122becf", "generation_seconds_batch": 27.26717461401131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2117253541946411, "target_z": -0.007812503769532035, "ce": 6.292664527893066, "genuineness": 4.017816066741943, "identity": 0.6765977144241333, "hypothesis": "J'ai trouvé la 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_Sourness/12d75e09a5931c0d04fd3437773a070edac78d3ae9618fff12ed92753a5353c7.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "132b428fbbaba977b33cf982222bee8d3b28f2e46763621ef4d05b486fb5798a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1c2c6598cc51ec6e203ce471428d0581529381f29999cfd038383066e8ed5f74", "generation_seconds_batch": 24.157243715017103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0909671038389206, "target_z": -0.2871093756731307, "ce": 5.990842819213867, "genuineness": 4.444586753845215, "identity": 0.32083141803741455, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/132b428fbbaba977b33cf982222bee8d3b28f2e46763621ef4d05b486fb5798a.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "13463b6128a6096c36de8fceee842c3708a8dc5466be85a5c89f7410e62073c0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "265be45d840aaff2923ee9bf0d0f4e9632308992d95b22bbd232011962c7ff2b", "generation_seconds_batch": 23.165557854925282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0495883971452713, "target_z": -0.38281251238560526, "ce": 5.974957466125488, "genuineness": 4.482243061065674, "identity": 0.736391007900238, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/13463b6128a6096c36de8fceee842c3708a8dc5466be85a5c89f7410e62073c0.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": "139b9d08374a5c75aced897026c6687b1873c4cbe7766cf95ed5ff6e499cff3c", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa1704280b2db0a7f80d797d0df103c4b27f25424c58ee60e87ea300e34ab3a4", "generation_seconds_batch": 19.44023312907666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11967885494232178, "target_z": -0.2207031280964013, "ce": 6.300607204437256, "genuineness": 4.532451152801514, "identity": 0.6638780236244202, "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_Sourness/139b9d08374a5c75aced897026c6687b1873c4cbe7766cf95ed5ff6e499cff3c.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "13e338cfb05e8476ac89a13f09cd8bfba25d860fea196e9c86aaae55a907c26e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "370f14186f62338be4ae5b731252e1317b38327b9b7fe181d1188027d97302f4", "generation_seconds_batch": 22.81100848002825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017498791217803955, "target_z": -0.4570312637318667, "ce": 5.637393951416016, "genuineness": 3.898571252822876, "identity": -0.11511484533548355, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/13e338cfb05e8476ac89a13f09cd8bfba25d860fea196e9c86aaae55a907c26e.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "143e4447e3831a548c2e9f2f5de76d8e38fdbe4ee483e210cc7b39266d12eaf5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "16f11b31975cead0cea0e939619a462ef1e3dc9eb8037a7916fce51f5e6dc5cb", "generation_seconds_batch": 23.95693270699121, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07998907566070557, "target_z": -0.31250001292410984, "ce": 6.09409761428833, "genuineness": 4.532451152801514, "identity": 0.6479920744895935, "hypothesis": "J'ai trouvé la 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_Sourness/143e4447e3831a548c2e9f2f5de76d8e38fdbe4ee483e210cc7b39266d12eaf5.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "14bb3c93f90eeb169dc187e670e56112bf0430398ae32b1b22ba4084c0eaf398", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f03e94f126caef8c2a8cb86817bc1e517d601f99f2a6ccd877e1a9715420d166", "generation_seconds_batch": 26.810802590101957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13910150527954102, "target_z": -0.175781265885885, "ce": 5.744620323181152, "genuineness": 4.406930446624756, "identity": 0.5575841069221497, "hypothesis": "J'ai trouvé la 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_Sourness/14bb3c93f90eeb169dc187e670e56112bf0430398ae32b1b22ba4084c0eaf398.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "15075dff9b59d27752449b1960b9db2c743478d2511da6caac427aa7ee726aa7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4340876cd93630a8352e4a9ab7f523d04918d02e08042fe9f59e6cef963b8604", "generation_seconds_batch": 24.366761011071503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04836934804916382, "target_z": -0.6093750183091556, "ce": 6.292664527893066, "genuineness": 4.494794845581055, "identity": 0.6417897939682007, "hypothesis": "J'ai trouvé la 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_Sourness/15075dff9b59d27752449b1960b9db2c743478d2511da6caac427aa7ee726aa7.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "f86ef94d1814d43ab7998427851f7706f92bc9540024c3957cd439fa0ebf27b0", "generation_seconds_batch": 17.865553620038554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04198823869228363, "target_z": -0.40039061140275944, "ce": 6.38003396987915, "genuineness": 4.331617832183838, "identity": 0.6327701807022095, "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_Sourness/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "15c7c11a2529ad0ea2ed43c0571abd050487ef653781041d8417ad5e40ff653a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "50ed6d675738e67c5acead0817cd590b21ea58e5ac748a2aef91f9f0731f67be", "generation_seconds_batch": 17.380377446999773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00023493170738220215, "target_z": -0.498046874057617, "ce": 6.300607204437256, "genuineness": 4.469690799713135, "identity": 0.4914352297782898, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/15c7c11a2529ad0ea2ed43c0571abd050487ef653781041d8417ad5e40ff653a.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "15e00ec939119f4a17c5aaee89a13641f807b2d38570145c0286944c4486a3de", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f9ca71d2db7ebba32b13e4922f9527cae2970e699a5e4225b07ed149c5c3c6a7", "generation_seconds_batch": 23.236022733035497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09687834978103638, "target_z": -0.2734374940764497, "ce": 6.1020402908325195, "genuineness": 4.268857479095459, "identity": 0.7459086179733276, "hypothesis": "De deur staat nog open. Ik heb je jas op het 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_Sourness/15e00ec939119f4a17c5aaee89a13641f807b2d38570145c0286944c4486a3de.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": "1681b6fedd8b778f43a6a14f4f4d9d53cce8c412e36f3520ded6c88faa6b48e4", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Your message arrived after I had left.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e3526c027e46de624418452d210a55a1353be958ae3880c6ef74e796b9fe191", "generation_seconds_batch": 19.412076186970808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0951894223690033, "target_z": -0.2773437459612157, "ce": 6.475345611572266, "genuineness": 4.105680465698242, "identity": 0.4307750463485718, "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_Sourness/1681b6fedd8b778f43a6a14f4f4d9d53cce8c412e36f3520ded6c88faa6b48e4.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "1697023cb8c81881cbbc6ec2f22aa3d32aeda94e9e737424eedb3674824d0e67", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8297c06d61ccccc7c853fc9fe5cb33b6e30cf9b242c8d97622e171dc56d7e13e", "generation_seconds_batch": 16.86777987203095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03945484757423401, "target_z": -0.40624998922990846, "ce": 6.332377910614014, "genuineness": 4.406930446624756, "identity": 0.5655839443206787, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1697023cb8c81881cbbc6ec2f22aa3d32aeda94e9e737424eedb3674824d0e67.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "17161e8caee56842b9d415c58525597624e4fd715e22546c84b62958a7efba59", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4171d46e5f45454ee54a2ead7654217cfe0c62ec18b46d7c0c88c8a0c3f65ca", "generation_seconds_batch": 24.535825594095513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05127732455730438, "target_z": -0.37890626050083925, "ce": 6.09409761428833, "genuineness": 4.243753433227539, "identity": 0.411006361246109, "hypothesis": "J'ai trouvé la 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_Sourness/17161e8caee56842b9d415c58525597624e4fd715e22546c84b62958a7efba59.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "17169f67cacde628b29f46b81366154f1438aa27cafecffde6f52e26b24ca710", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "31b1f018f0fed4d57d9e8b866f15942e5fd0c3a225d50b40d84967e46f107b3b", "generation_seconds_batch": 17.99024648591876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1306568682193756, "target_z": -0.1953125253097151, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.40101906657218933, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/17169f67cacde628b29f46b81366154f1438aa27cafecffde6f52e26b24ca710.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "171c55b73408271f92120d136ce7fdd3b28fc19a7ab5b76a96909d78ad5ed0b1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7b85fefe6feb8b113f98a1a853ee2b91231cd88f120d17fd59d0e832a6961b5d", "generation_seconds_batch": 24.223486138042063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04789946973323822, "target_z": -0.3867187642703713, "ce": 6.165581703186035, "genuineness": 3.973883628845215, "identity": 0.19710591435432434, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/171c55b73408271f92120d136ce7fdd3b28fc19a7ab5b76a96909d78ad5ed0b1.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "17285369a402f4c92994cf3b57ca02c9ff75ee15ed3ad0c8ce17f6413e77a834", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cce1d7a2d1f50658f1661d8ff3dc2926fdaf6ff49641e8565e035ce03a4e6b68", "generation_seconds_batch": 24.06782561703585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7015140652656555, "target_z": 1.1249999913839268, "ce": 5.967014789581299, "genuineness": 4.118232727050781, "identity": 0.6404502987861633, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/17285369a402f4c92994cf3b57ca02c9ff75ee15ed3ad0c8ce17f6413e77a834.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "17635f4a746caa94cfc441b11af1a6455a8ee1ffd47d2fe0a8de4e2d68b26729", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "edd1229c68b394a9294160da580a288ab950f2fd1fdca4a09cea4b2099fc46ab", "generation_seconds_batch": 18.378422364010476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10278958827257156, "target_z": -0.259765629711915, "ce": 6.038498878479004, "genuineness": 4.381826400756836, "identity": 0.7897001504898071, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/17635f4a746caa94cfc441b11af1a6455a8ee1ffd47d2fe0a8de4e2d68b26729.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "1837480c6c518e7b57fa93061221ee33cf32cb5f22130245b745e875491a3879", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3ec8e3f0bce5abe3f6b1a68d945ef5029963c4c021757ef315445a199c05da75", "generation_seconds_batch": 22.515159595990553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13741257786750793, "target_z": -0.17968751777065103, "ce": 6.09409761428833, "genuineness": 4.017816066741943, "identity": 0.2878704071044922, "hypothesis": "The 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_Sourness/1837480c6c518e7b57fa93061221ee33cf32cb5f22130245b745e875491a3879.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "1970ac6f2e89c00093b6969942dc7c28aaaa77a23a0e601a9adb01db78c7cd72", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3032e2f815515643b79307b4ddcca51ec18b24a1a4830ff6495713be3e3d9051", "generation_seconds_batch": 25.260001125978306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.041613638401031494, "target_z": -0.5937500107700915, "ce": 6.523001670837402, "genuineness": 4.457139015197754, "identity": 0.5827566385269165, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1970ac6f2e89c00093b6969942dc7c28aaaa77a23a0e601a9adb01db78c7cd72.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "1970bf1a9428278a3d831b72c7dae5d27076b36c5892efd10d5b5ba7dae5a185", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "557affdf9f9dfa034c1e814c40c15c416ae6b3e4444924a93730f723f1ce3d45", "generation_seconds_batch": 22.375873242039233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12052331864833832, "target_z": -0.2187500021540183, "ce": 5.895530700683594, "genuineness": 4.024092197418213, "identity": 0.5071665048599243, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1970bf1a9428278a3d831b72c7dae5d27076b36c5892efd10d5b5ba7dae5a185.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "19ac34f1ada531469ddf5a6ae2bbf73af5717a14ce92f95ba8f535580680b447", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d00977c7d7c5622c1ce8cb2968948c3386dd6f0a788be19117c460c787f31d08", "generation_seconds_batch": 24.307108124019578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03992471098899841, "target_z": -0.5898437588853255, "ce": 6.173524379730225, "genuineness": 4.356721878051758, "identity": 0.5655251741409302, "hypothesis": "J'ai trouvé la 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_Sourness/19ac34f1ada531469ddf5a6ae2bbf73af5717a14ce92f95ba8f535580680b447.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "19c86432b91cace1830abffd6b14d483f52745457a4b0973ff346f95f476037b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a646c58ff78f235c7f779a256540b4042273918317f7c5f0e85dd8be7370717", "generation_seconds_batch": 24.435832643997855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6204456090927124, "target_z": 0.9375000387723295, "ce": 5.6532793045043945, "genuineness": 3.537698984146118, "identity": 0.3796404004096985, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/19c86432b91cace1830abffd6b14d483f52745457a4b0973ff346f95f476037b.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "1a3e5cc05c4e3a2274f2001cfc43437bdd458febedd855e58343138abb772bd3", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "64fe979d5fc24754ed56e09df71dbe2aa7fd9fdbde1261a46d5c42c826a767e7", "generation_seconds_batch": 25.814593910006806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09350049495697021, "target_z": -0.2812499978459817, "ce": 6.078212261199951, "genuineness": 4.319066047668457, "identity": 0.6873383522033691, "hypothesis": "J'ai trouvé la 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_Sourness/1a3e5cc05c4e3a2274f2001cfc43437bdd458febedd855e58343138abb772bd3.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "1a4438b1d2733d277d04afc06f9c19aa5ac4890f8a037578738c98d1df54787e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9f3d4466cf8f13aff015fc12462f95ff9f9b438de7d182873e1a649b5506a215", "generation_seconds_batch": 25.14225311006885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03692145645618439, "target_z": -0.4121093670570575, "ce": 6.221180438995361, "genuineness": 4.582659721374512, "identity": 0.7079700231552124, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1a4438b1d2733d277d04afc06f9c19aa5ac4890f8a037578738c98d1df54787e.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "1a6c447e68f19bcd3c23417ce7e43fe8ade88f9f30af417c31feb73d0e07cb39", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4239c95fe21a0d971a4ad1103b52cb7b55708e801320c62352ec4f274581bf3f", "generation_seconds_batch": 26.347491367021576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9242968559265137, "target_z": 3.9531248395256364, "ce": 5.391171455383301, "genuineness": 3.5565271377563477, "identity": 0.47275781631469727, "hypothesis": "De deur 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_Sourness/1a6c447e68f19bcd3c23417ce7e43fe8ade88f9f30af417c31feb73d0e07cb39.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "1abc1372cad9a0f8a31f7b4d9cba66287e2d3b0bdd5d65556de5665d957bcc73", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c4ae9aeab375be4351d950ebf153472998955fc9e8c4e255ec1e4b8cc1672cf2", "generation_seconds_batch": 23.873969059903175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12474563717842102, "target_z": -0.20898437244210327, "ce": 6.205295085906982, "genuineness": 4.457139015197754, "identity": 0.6682069897651672, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1abc1372cad9a0f8a31f7b4d9cba66287e2d3b0bdd5d65556de5665d957bcc73.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "1b36560fee23d1498c88edf0064b336f6fdf947b67043cd132d1d111cab1f0be", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "41580182e92783389272d409322d3761ab38d9bbfb077b29ddee768115154b85", "generation_seconds_batch": 25.649096712935716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019187718629837036, "target_z": -0.4531250118471007, "ce": 6.356205940246582, "genuineness": 4.036643981933594, "identity": 0.30219507217407227, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1b36560fee23d1498c88edf0064b336f6fdf947b67043cd132d1d111cab1f0be.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "1b7347a4fc6420f7db4bbd504d5df611be26e314d08c44d8fd9159c795c2675e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b08588aaeaba95cedbe9be08ed4799b0f343a5d2826dc493a7b30eb10cd1cee6", "generation_seconds_batch": 24.28647373407148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04789946973323822, "target_z": -0.3867187642703713, "ce": 6.316492557525635, "genuineness": 4.256305694580078, "identity": 0.30128014087677, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1b7347a4fc6420f7db4bbd504d5df611be26e314d08c44d8fd9159c795c2675e.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": "1bc73d40333924f9f9219bc90754c8c7442789dfdaf0dac0994fc74486b90bef", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Escribí el número en el sobre.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c9dfd21bc38a3abfb9d3494714428f355e54651a61e8d2c54df88c4e59b5bcc", "generation_seconds_batch": 14.429744503926486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05296625196933746, "target_z": -0.37500000861607324, "ce": 6.157639026641846, "genuineness": 4.137060642242432, "identity": 0.4728858470916748, "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_Sourness/1bc73d40333924f9f9219bc90754c8c7442789dfdaf0dac0994fc74486b90bef.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "1c374447c8b541e887960d549a326c741a59d33fe3483c1b66095b4dd3c6dada", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f6d06c6d08f6ecd27ece85d986479c3b2c84ea2d07ef9719f0bffee915557362", "generation_seconds_batch": 24.569044049014337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021721109747886658, "target_z": -0.4472656340199517, "ce": 5.804190158843994, "genuineness": 4.162164688110352, "identity": 0.5248020887374878, "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_Sourness/1c374447c8b541e887960d549a326c741a59d33fe3483c1b66095b4dd3c6dada.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "1c59401be250dd121e8b75e7e0934184982e1328c468ffc199b4f20ef1b06540", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4b7d8c09074d8d5dbd3acfd20e516cffd15a34f45370763a119946b716f3c93c", "generation_seconds_batch": 25.343290459015407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016654327511787415, "target_z": -0.4589843896742497, "ce": 6.141753673553467, "genuineness": 4.6705241203308105, "identity": 0.6291144490242004, "hypothesis": "J'ai trouvé la 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_Sourness/1c59401be250dd121e8b75e7e0934184982e1328c468ffc199b4f20ef1b06540.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "1c96cd0f8360ea03b784948d8683e1feaab9705cd56c38ffd8fba53aa09d2c0f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fb745423875051f639902d26bb67648862ffe6a0cbbb7af2400218bc2477b106", "generation_seconds_batch": 26.328787826001644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015809863805770874, "target_z": -0.4609375156166327, "ce": 6.23706579208374, "genuineness": 4.632867813110352, "identity": 0.774273157119751, "hypothesis": "J'ai trouvé la 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_Sourness/1c96cd0f8360ea03b784948d8683e1feaab9705cd56c38ffd8fba53aa09d2c0f.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "0efea609ccd9eb504e0c9b5d95085335dcbd10c3a4b1c839e793e8aa7b7b7cd9", "generation_seconds_batch": 18.444242827012204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05803303420543671, "target_z": -0.36328125296177516, "ce": 6.181467056274414, "genuineness": 4.13078498840332, "identity": 0.6260890960693359, "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_Sourness/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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "d1f091a29bdbd7b80037d6a58ba12c58d486ef9c5987ef73ddb1e93db716582d", "generation_seconds_batch": 20.19896266690921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05887749791145325, "target_z": -0.36132812701939215, "ce": 6.252951145172119, "genuineness": 4.457139015197754, "identity": 0.691382110118866, "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_Sourness/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "1db9e771d78cebe8bc32545c75e234de809424444d66efb892462e9b210fbbd6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "134293ffda2c5ab247b66e0278ef1b7042679404a0e4111613d1e62588be9c04", "generation_seconds_batch": 25.11398461693898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08590032160282135, "target_z": -0.29882813132742875, "ce": 6.109982967376709, "genuineness": 4.325342178344727, "identity": 0.781234860420227, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1db9e771d78cebe8bc32545c75e234de809424444d66efb892462e9b210fbbd6.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "1e2ff20978dd591333ae6b75d84ca94b11a58c09666bed4c344b003569a2d2cc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8c788137bfe109d04c7a07d4608ac096e91d8fe1b28fc807d3790c4b4a896370", "generation_seconds_batch": 24.936348365969025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1576797068119049, "target_z": -0.1328124951534588, "ce": 6.046441555023193, "genuineness": 4.570107460021973, "identity": 0.6711896657943726, "hypothesis": "Ik 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_Sourness/1e2ff20978dd591333ae6b75d84ca94b11a58c09666bed4c344b003569a2d2cc.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "1ead743ae7860a9e9306c68a77a06d3bb506be1cd7bd49f93dc37d53076332f6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "528f9dc5a59ca092c4984ed01706e393c42a3bf6b5d37777822474cfc1cf6068", "generation_seconds_batch": 19.576854366925545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30208292603492737, "target_z": 0.20117186867257122, "ce": 6.173524379730225, "genuineness": 4.149612903594971, "identity": 0.5238713026046753, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1ead743ae7860a9e9306c68a77a06d3bb506be1cd7bd49f93dc37d53076332f6.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": "1eae7225559af33e9930dc21e5619aa3b13dbaafc862aec221e72d52b95f271d", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The keys are on the kitchen table.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8891d33258aa40264880663908d0ad71215839803d6c0d21b9d7cd6a3bc1c9d7", "generation_seconds_batch": 25.321224396000616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0951894223690033, "target_z": -0.2773437459612157, "ce": 6.292664527893066, "genuineness": 4.193545341491699, "identity": 0.41371360421180725, "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_Sourness/1eae7225559af33e9930dc21e5619aa3b13dbaafc862aec221e72d52b95f271d.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "2b144d0b549343d97103715b151c3ac3e471e70a38d9c3b83c20eb5240acd774", "generation_seconds_batch": 18.444242827012204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05887749791145325, "target_z": -0.36132812701939215, "ce": 6.213237762451172, "genuineness": 4.482243061065674, "identity": 0.6362947225570679, "hypothesis": "Escribí el número en el sobre, léello bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "1f5dd391c00efc2c7eb17083eb75785ac29679c361cea27c2fa6670503bd2db2", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e6d5d49740ff1b770d28140dd419f9e8e6f02844c71dc325a8a7beebf61343f", "generation_seconds_batch": 23.95693270699121, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020032182335853577, "target_z": -0.4511718859047177, "ce": 5.967014789581299, "genuineness": 4.218649387359619, "identity": 0.48959335684776306, "hypothesis": "J'ai trouvé la 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_Sourness/1f5dd391c00efc2c7eb17083eb75785ac29679c361cea27c2fa6670503bd2db2.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": "1f6cc932956540a728dc3e98c2af86dd3d205860ccfdc607cdd2efe2cfbb0469", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "921e8f43b1b8b720ffda1b9b8cc7aec1e39b0c90783b8036bbe7b9756704a45f", "generation_seconds_batch": 19.44023312907666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09181156754493713, "target_z": -0.2851562497307477, "ce": 6.316492557525635, "genuineness": 4.394378662109375, "identity": 0.5127482414245605, "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_Sourness/1f6cc932956540a728dc3e98c2af86dd3d205860ccfdc607cdd2efe2cfbb0469.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "2033a7cf91216f5ccbc999461d7d10a03d6edf4092659b014187221d77f3d2f5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "73ad06c0e2c9a67bbff4f0f6a8a86b3cdc7bd08ec7bdaa5d480ab05956f5acd2", "generation_seconds_batch": 15.747760157100856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18132467567920685, "target_z": -0.07812500323102746, "ce": 5.458683967590332, "genuineness": 3.848362922668457, "identity": 0.5145748853683472, "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_Sourness/2033a7cf91216f5ccbc999461d7d10a03d6edf4092659b014187221d77f3d2f5.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "204a46da5abf5b2d7286fa8ed72e1c3f2e5b8c40b82dc0dc50c437d5d7625f7c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a161188e4eb03919c424255e1d37ae87065884768f5d26a0f8362832bc5924b8", "generation_seconds_batch": 26.987835936015472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05887749791145325, "target_z": -0.36132812701939215, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.7976066470146179, "hypothesis": "J'ai trouvé la 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_Sourness/204a46da5abf5b2d7286fa8ed72e1c3f2e5b8c40b82dc0dc50c437d5d7625f7c.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "2093eb2e53562e270e02d2aeb3c7b31d69a1bd620c6c54fc0b86e856ce6b511f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cae350f1eee2e5043048b64a419fdba1c5379b026dc9bb0aaad295ade93cc7b5", "generation_seconds_batch": 23.774941900046542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03607699275016785, "target_z": -0.4140624929994405, "ce": 5.8875885009765625, "genuineness": 4.005263805389404, "identity": 0.5235309600830078, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2093eb2e53562e270e02d2aeb3c7b31d69a1bd620c6c54fc0b86e856ce6b511f.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "20cde5e46a6606b8617906fb3fa2624d88d8fb5261dd759c813a1547dde0f4e5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "03d8ae4763f19d8946290092df539229477595209648e859943237537b0d1dd4", "generation_seconds_batch": 23.234118802007288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09856727719306946, "target_z": -0.2695312421916836, "ce": 6.109982967376709, "genuineness": 3.9173994064331055, "identity": 0.4156215190887451, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/20cde5e46a6606b8617906fb3fa2624d88d8fb5261dd759c813a1547dde0f4e5.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "20de45865c05ed9c45a0f934d6c0f5463cece5bc82473f9d957d49f4a244f65b", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "329dceda425543ae5945bfa4b1a7f2651ba5d8e3d82fa696e3980d25fe6856d5", "generation_seconds_batch": 17.678999888012186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033543601632118225, "target_z": -0.41992187082658955, "ce": 5.935244083404541, "genuineness": 4.20609712600708, "identity": 0.5629066228866577, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/20de45865c05ed9c45a0f934d6c0f5463cece5bc82473f9d957d49f4a244f65b.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "217a3198ccbc78e4b8aeca8c0e89811cd115d62784331602af4fc696bbb8425b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cb4ba56b948669f6f1e21ddab93b04c679a3e1ad90b30c3593adc208d1f76c0c", "generation_seconds_batch": 16.064682033029385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05043286085128784, "target_z": -0.38085938644322226, "ce": 5.967014789581299, "genuineness": 4.193545341491699, "identity": 0.5438169240951538, "hypothesis": "J'ai trouvé la 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_Sourness/217a3198ccbc78e4b8aeca8c0e89811cd115d62784331602af4fc696bbb8425b.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": "229ad7d5c78f865fafd0d7360d8ae20a5a06893cb1277bb5c94d795238be3d6e", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05554c1c805fca1e3169c4e158ac5b39b14ede4b80837c756cfdefdd19bfb7b2", "generation_seconds_batch": 18.39402201701887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08590032160282135, "target_z": -0.29882813132742875, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.5858940482139587, "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_Sourness/229ad7d5c78f865fafd0d7360d8ae20a5a06893cb1277bb5c94d795238be3d6e.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "2477b5cf40479be8f654280a0b67bec8625e43d3f49cabbe3e7ab5780fb0297f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eefc1032031995da88804b48791b42da3483d8b3cf20f3a9ffff4cb439dcc96f", "generation_seconds_batch": 21.62407969601918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08167800307273865, "target_z": -0.30859376103934383, "ce": 5.871703147888184, "genuineness": 4.18099308013916, "identity": 0.6240903735160828, "hypothesis": "J'ai trouvé la 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_Sourness/2477b5cf40479be8f654280a0b67bec8625e43d3f49cabbe3e7ab5780fb0297f.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "25ec9680eb9a980132f1d31f440681b29a0204bb14694ae1b808f3428187d982", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ad3b9852f9cc4a1c23ba5a62761b2ddfd343871a5d5156f42991b61f4a3c0aa2", "generation_seconds_batch": 26.48452864808496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14585721492767334, "target_z": -0.16015625834682093, "ce": 6.252951145172119, "genuineness": 4.6203155517578125, "identity": 0.7707399725914001, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/25ec9680eb9a980132f1d31f440681b29a0204bb14694ae1b808f3428187d982.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "25f7438e939d68cbf9af48a2d2cc8903621b757e33971fb267c55dbf2d8976df", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ac6266cee3665a90f222f1604ac2c491e85f312ec0de6fb7108744c0ce4074f", "generation_seconds_batch": 22.375873242039233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11207868903875351, "target_z": -0.23828124434570194, "ce": 5.665193557739258, "genuineness": 3.8044304847717285, "identity": 0.5724436044692993, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/25f7438e939d68cbf9af48a2d2cc8903621b757e33971fb267c55dbf2d8976df.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": "2621b79180c0d9cf61d32d879998b9577885e7c4b175fddb5432f6969426e7f9", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59d789efaf8e117d316d871a6bbb8545c8b1744f628111c8e822d64c08ecf530", "generation_seconds_batch": 28.665839366032742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07492230832576752, "target_z": -0.324218734114115, "ce": 6.125868320465088, "genuineness": 4.118232727050781, "identity": 0.4878232479095459, "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_Sourness/2621b79180c0d9cf61d32d879998b9577885e7c4b175fddb5432f6969426e7f9.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "2637d31a1413c49233c42d440048eaf856f5e9b583f36bc50c1f9c4b80f01fce", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "df77ca9f2c69a125b9994f9d0676faf9b16bb04e9d2453d0872896b931a2b07f", "generation_seconds_batch": 17.90749287197832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00023493170738220215, "target_z": -0.498046874057617, "ce": 6.173524379730225, "genuineness": 4.369274139404297, "identity": 0.6388704776763916, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2637d31a1413c49233c42d440048eaf856f5e9b583f36bc50c1f9c4b80f01fce.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": "268a1b714d5efae43d9fdb98cf2522f9368ab16127159a5d2762604af54b33c8", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "376955cf21899a45cb99bc9001f26122dd18591eecbecf0c966e86166d892ceb", "generation_seconds_batch": 17.991890819044784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14585721492767334, "target_z": -0.16015625834682093, "ce": 6.006728172302246, "genuineness": 4.545003414154053, "identity": 0.8839935064315796, "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_Sourness/268a1b714d5efae43d9fdb98cf2522f9368ab16127159a5d2762604af54b33c8.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": "26b46c20076114a59bb130ed508223ef8d585f7c0092ea39f32a1de09b854aad", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca6097b59ee492b48cbaedb1eeb21d82a8127e679b93097c06393a270fb2823e", "generation_seconds_batch": 15.37391107599251, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14754614233970642, "target_z": -0.15625000646205492, "ce": 6.125868320465088, "genuineness": 4.545003414154053, "identity": 0.5998754501342773, "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_Sourness/26b46c20076114a59bb130ed508223ef8d585f7c0092ea39f32a1de09b854aad.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "26c14286ab3606f96c7f7e494fa4dca96a409165e08e2d618118dd8282e4b382", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4e02c53448bbf5103be229f9675ccff81f41b075c63ee47a7778f728a7184090", "generation_seconds_batch": 24.8731915949611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03945484757423401, "target_z": -0.40624998922990846, "ce": 6.0146708488464355, "genuineness": 4.469690799713135, "identity": 0.45925217866897583, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/26c14286ab3606f96c7f7e494fa4dca96a409165e08e2d618118dd8282e4b382.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "82d6cc649f6db4b62debd4a01b7c286e0935dbc1d60f87d9da5f48139f8119e8", "generation_seconds_batch": 15.296974314027466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0495883971452713, "target_z": -0.38281251238560526, "ce": 6.467403411865234, "genuineness": 4.394378662109375, "identity": 0.4343693256378174, "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_Sourness/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "2730971d1622e1a8ad953ed25b5ab2aa2e82b3f9a7abf1ce3360baf479b3535e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8695a158fd938e30ded5aa49bb363400e98324736601446e28c230697bebbf45", "generation_seconds_batch": 17.08024485502392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054655179381370544, "target_z": -0.3710937567313072, "ce": 6.165581703186035, "genuineness": 4.362998008728027, "identity": 0.3488355278968811, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2730971d1622e1a8ad953ed25b5ab2aa2e82b3f9a7abf1ce3360baf479b3535e.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": "2784b44654e9c8dc9526a35b45b52c0ac904048fab21b168c9ad96c605fc58a6", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c7daaa9a46036f524e1a96f3b19a8263a16dc1cfa529d594223d630c034f8e34", "generation_seconds_batch": 22.423677165992558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10447851568460464, "target_z": -0.255859377827149, "ce": 6.109982967376709, "genuineness": 4.507347106933594, "identity": 0.5705941915512085, "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_Sourness/2784b44654e9c8dc9526a35b45b52c0ac904048fab21b168c9ad96c605fc58a6.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "27d7bef69e9bd7a8062bb2ba400fc6123d02fa7ea97e8019f663555fd834f23f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "01805e1e07c2fe87269f74b214b9c8d4699056ba83dde0b110c6cd810d271465", "generation_seconds_batch": 22.779177734977566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2049696445465088, "target_z": -0.023437511308596105, "ce": 5.7406487464904785, "genuineness": 3.8922953605651855, "identity": 0.3920416831970215, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/27d7bef69e9bd7a8062bb2ba400fc6123d02fa7ea97e8019f663555fd834f23f.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "282e7105f8f0b5402269fb376dcc98ad937ea38ec07dca3c37f130bedf95ac09", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4e0ad99118e7d2c4a8c13c4a62e07710e6f574bcceeac06a0a31249bb3eedb6", "generation_seconds_batch": 23.999825958977453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007835105061531067, "target_z": -0.515625007539064, "ce": 6.300607204437256, "genuineness": 4.532451152801514, "identity": 0.5797075629234314, "hypothesis": "J'ai trouvé la 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_Sourness/282e7105f8f0b5402269fb376dcc98ad937ea38ec07dca3c37f130bedf95ac09.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "28424cbb9cd1e5df7017108b606d260a393db42bc058d58d6e11b2b075501efd", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e0f17a1af0bde472e54de45bfdedc58edf4ebb8d7942c3ca0580cf1da79ea7ce", "generation_seconds_batch": 25.178357504075393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5527331829071045, "target_z": 3.0937502520201416, "ce": 6.062326908111572, "genuineness": 4.055472373962402, "identity": 0.3475611209869385, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/28424cbb9cd1e5df7017108b606d260a393db42bc058d58d6e11b2b075501efd.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "2845d5cc4f9d0fe40213b21f78a13646102adaa948e41ea40a90915beca3c1dd", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "27dd9613289bbe2db40f2338bc4f2d83c17aea0aacad05a8cf83dcbe596e6186", "generation_seconds_batch": 22.1632325979881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17794682085514069, "target_z": -0.0859375070005595, "ce": 5.756534099578857, "genuineness": 3.9048471450805664, "identity": 0.6688276529312134, "hypothesis": "J'ai trouvé la 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_Sourness/2845d5cc4f9d0fe40213b21f78a13646102adaa948e41ea40a90915beca3c1dd.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "288df117c1b75196df22d62d07f16808eace2452d362137cd613a1f54e9a93f7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "61531019c1f01fcb85c64b7a6f687372e754bff40bcd3cb5b317be50ea5c9265", "generation_seconds_batch": 23.989061560947448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031010210514068604, "target_z": -0.42578124865373856, "ce": 5.6334228515625, "genuineness": 4.250029563903809, "identity": 0.5883749723434448, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/288df117c1b75196df22d62d07f16808eace2452d362137cd613a1f54e9a93f7.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "28c4754f397a9c7756c73240f5e209adfdd080ba3952bd754fe06704f78e983b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1ef08dfef52a8a5a8f6e578af962ff4cd7e277dcc5b2a69147290f88b9b8199f", "generation_seconds_batch": 18.19853241799865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16950219869613647, "target_z": -0.10546873196009669, "ce": 5.577824115753174, "genuineness": 3.9048471450805664, "identity": 0.6283377408981323, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/28c4754f397a9c7756c73240f5e209adfdd080ba3952bd754fe06704f78e983b.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "2923fbe82d4cd9a2c0601814dacc6832f998ae7524174c2f9e2313424ed8f64e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b88be7a466cdb989d929e8270c50e7d8dccb80d8b30f8454591b16b62e9b2063", "generation_seconds_batch": 24.19409443391487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006520777940750122, "target_z": -0.4824218665185529, "ce": 5.7406487464904785, "genuineness": 4.218649387359619, "identity": 0.5819620490074158, "hypothesis": "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_Sourness/2923fbe82d4cd9a2c0601814dacc6832f998ae7524174c2f9e2313424ed8f64e.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "2a0c8e9a5695d0e77ea11d326f952502b658b2f3fea9ffca13448e850a08b0e6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "18f0a271842e5ddd9bd3e975f66725448b6845cd5ada8386e36493e3d3c9a932", "generation_seconds_batch": 24.54062028496992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.034388065338134766, "target_z": -0.41796874488420654, "ce": 6.213237762451172, "genuineness": 4.262581825256348, "identity": 0.5122740268707275, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2a0c8e9a5695d0e77ea11d326f952502b658b2f3fea9ffca13448e850a08b0e6.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "2b87e4f8a02dc8aedaf8c7a24e123e7eb31c0614b5652786618a9eec85012a21", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "877ef8758825c4b9f12607cc55aeb139b0ca10d30c00c159241afbc652dd1a7d", "generation_seconds_batch": 22.693542191991583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3654176592826843, "target_z": 0.3476562109584182, "ce": 5.927301406860352, "genuineness": 3.7793264389038086, "identity": 0.3681023120880127, "hypothesis": "The 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_Sourness/2b87e4f8a02dc8aedaf8c7a24e123e7eb31c0614b5652786618a9eec85012a21.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "2c3ce60d75e7c296ca9f09176af23352f6d4f3e8739f4d05516e57245fb93287", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bb5bfff1e721b3b753a5cd6725be0a69fc9f3f0e779e02221186f791b71ee6b0", "generation_seconds_batch": 17.380377446999773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011212959885597229, "target_z": -0.5234375113085961, "ce": 6.403861999511719, "genuineness": 4.532451152801514, "identity": 0.374377578496933, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2c3ce60d75e7c296ca9f09176af23352f6d4f3e8739f4d05516e57245fb93287.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": "2c76cf88c9a5c232d8a8e4f8eee80cd173b1ca247a72c10b21ecc749f01927a9", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa8106a2a769efe0e5a2caf4e649245bc3cb0f07121dcb95cc8001c07d6e6ccc", "generation_seconds_batch": 23.291984883951955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6675801277160645, "target_z": 3.359375104469888, "ce": 6.149696350097656, "genuineness": 3.936227321624756, "identity": 0.5603836178779602, "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_Sourness/2c76cf88c9a5c232d8a8e4f8eee80cd173b1ca247a72c10b21ecc749f01927a9.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "2c9ae011096ebe4b82e6e9cde9cbac6ae5cbef5e0dbcb20791637129fbf12bc7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "efa8fc63f6937ed6c17831dc68e6459897fff6f5e7e4cc59308b3026f649f413", "generation_seconds_batch": 32.96372454997618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1078563705086708, "target_z": -0.248046874057617, "ce": 5.998785495758057, "genuineness": 4.243753433227539, "identity": 0.6092857718467712, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2c9ae011096ebe4b82e6e9cde9cbac6ae5cbef5e0dbcb20791637129fbf12bc7.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": "2d14b95ac04aab76668efe4c6d60dcfac171f3cd0197ebf8a3945a18fabc4fae", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e76e30413b137c38b040d831fff861dda71ec5905deb37a27e2645ff98742117", "generation_seconds_batch": 21.343607635004446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035232529044151306, "target_z": -0.41601561894182354, "ce": 6.268836498260498, "genuineness": 3.773050308227539, "identity": 0.4245278537273407, "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_Sourness/2d14b95ac04aab76668efe4c6d60dcfac171f3cd0197ebf8a3945a18fabc4fae.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "2d420120e045830c6d4649e29fbd4e04862cd0e796392b51e1f6172dbcca4a93", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d3d73553df64a6faf1d93577c305b7870c75dcbcbbc1f06394ac0884c094f728", "generation_seconds_batch": 25.890148665988818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02425450086593628, "target_z": -0.4414062561928026, "ce": 6.221180438995361, "genuineness": 4.13078498840332, "identity": 0.411650687456131, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2d420120e045830c6d4649e29fbd4e04862cd0e796392b51e1f6172dbcca4a93.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "2db8ba60b34c27dc94e7e9573303f5da284ce130e37039ad14cf93571dc3085d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "848d5d97fd91a979c82dc79ba0415bc0dec8fbb1e2a5274b2232379dce553f10", "generation_seconds_batch": 22.155616548960097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10616744309663773, "target_z": -0.251953125942383, "ce": 6.2767791748046875, "genuineness": 4.507347106933594, "identity": 0.6031569242477417, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2db8ba60b34c27dc94e7e9573303f5da284ce130e37039ad14cf93571dc3085d.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "2dc5f5975c8cd641765a9e63382c30303a09233619579d21948e513b3e76d488", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bc5e5d1d73c3a4f1d63731d0495c9bf6cfc1a2fb273c802b343fcd3150c3a46d", "generation_seconds_batch": 18.20911829790566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26239314675331116, "target_z": 0.1093749838448627, "ce": 5.974957466125488, "genuineness": 3.613011360168457, "identity": 0.5882257223129272, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2dc5f5975c8cd641765a9e63382c30303a09233619579d21948e513b3e76d488.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "2e046393b4b61919b59ca98b30866f36f67c475b559d232ecefebbd7eeeb8dc8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3948411b2ffdf7d1d2862cc3f380a61d975487df6e575827ebb009d9b54f984a", "generation_seconds_batch": 23.17332083999645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2835047245025635, "target_z": 0.15820309794014503, "ce": 6.157639026641846, "genuineness": 4.256305694580078, "identity": 0.3356277048587799, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2e046393b4b61919b59ca98b30866f36f67c475b559d232ecefebbd7eeeb8dc8.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "2e7a48d5058ea2077d3d452ee9cfe07c262cfac5fd971836c0ba4dd7484b3dc4", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "72c92ff678ce4d82c7c46dd738a7a94c588910d002bfc58d7773317057624f22", "generation_seconds_batch": 16.83630693005398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 6.213237762451172, "genuineness": 4.268857479095459, "identity": 0.390852689743042, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2e7a48d5058ea2077d3d452ee9cfe07c262cfac5fd971836c0ba4dd7484b3dc4.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "2ec4d0787d66c790cf0b97611028350f8e3d9ed65b752dfb834abdc2e2f82c71", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "37464eba07fbf8331c7f2f4e46c870690ad1f87c6cb952634f6a677e0fe37f03", "generation_seconds_batch": 17.190000729984604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0723889172077179, "target_z": -0.330078111941264, "ce": 6.308549880981445, "genuineness": 4.469690799713135, "identity": 0.8374737501144409, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2ec4d0787d66c790cf0b97611028350f8e3d9ed65b752dfb834abdc2e2f82c71.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "2ed2e8023add3e75fb735b106c8a3ef8ea9a3ead2e42f584bd2ac4a61bd235d5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "389134ce1b6a7f5677a46276da0276fc8d2f1048d17f994a8abb89eae43b39f8", "generation_seconds_batch": 16.563104749075137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11207868903875351, "target_z": -0.23828124434570194, "ce": 5.748591423034668, "genuineness": 4.406930446624756, "identity": 0.5152653455734253, "hypothesis": "J'ai trouvé la 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_Sourness/2ed2e8023add3e75fb735b106c8a3ef8ea9a3ead2e42f584bd2ac4a61bd235d5.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "2f18d039e95dd53d2ad11787a57cc67a08e7eede7eb510362a41e6351436ab09", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "075f338d153bd408944e8b169f314580f5f6c202540726e203a869db18d849cd", "generation_seconds_batch": 23.752512108068913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.917541265487671, "target_z": 3.9375001077009153, "ce": 5.5738525390625, "genuineness": 3.578493118286133, "identity": 0.29774245619773865, "hypothesis": "De deur 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_Sourness/2f18d039e95dd53d2ad11787a57cc67a08e7eede7eb510362a41e6351436ab09.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": "2f475882d6ae192199412d623e0bd0bbebc4c620423d0fe5f2e3e1ef0fb4e059", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4b6aed388350e6e2be1c20fd87cb468cb4f340697d0542d7bd7e29911a503b4", "generation_seconds_batch": 17.991890819044784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10110066086053848, "target_z": -0.26367188159668103, "ce": 5.9431867599487305, "genuineness": 4.432034492492676, "identity": 0.7147089242935181, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña huerta de madera. Te esperaré al otro lado.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2f475882d6ae192199412d623e0bd0bbebc4c620423d0fe5f2e3e1ef0fb4e059.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": "2f55f4ab0549e0130087dee78ce1db4ad1d5786f97a98f88d17b3f7678c46c0e", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "15bdfcc1f141de1d48b7407387b72c8221490c581326f5e8280760a14cc92fdd", "generation_seconds_batch": 18.88043193600606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16527986526489258, "target_z": -0.11523439613630462, "ce": 6.109982967376709, "genuineness": 4.394378662109375, "identity": 0.6744748950004578, "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_Sourness/2f55f4ab0549e0130087dee78ce1db4ad1d5786f97a98f88d17b3f7678c46c0e.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "2f5b106ce0b59ff00dca7c8e448cb6122296a6a4a88a1129dcd09c583c7239de", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0f26336b2bff5234a38e953b815c875cfe0772aeeea013e11335169140ed8326", "generation_seconds_batch": 23.656512449029833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09603388607501984, "target_z": -0.2753906200188327, "ce": 6.038498878479004, "genuineness": 4.632867813110352, "identity": 0.6014965772628784, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2f5b106ce0b59ff00dca7c8e448cb6122296a6a4a88a1129dcd09c583c7239de.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "2fb7aed3d93319515b4d0ab15f59c163af40cf77a074a3f6ebacf21b07c17ab9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "040eb01df4ae811bad5d77f9bb7201ed755ee3e7b567f75e62b3a40f254ef239", "generation_seconds_batch": 22.53122924407944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25225958228111267, "target_z": 0.0859374725362666, "ce": 6.022613525390625, "genuineness": 4.080576419830322, "identity": 0.5725816488265991, "hypothesis": "La porque 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_Sourness/2fb7aed3d93319515b4d0ab15f59c163af40cf77a074a3f6ebacf21b07c17ab9.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "2fc981dc1685c68f7bab67e23f2c9c2eb17e1810fc3a4d43a60e69a4babfc242", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "37567969086a34ac2b2eb68c89e032eadb3adbd46c636f05dbff1f0b87c1d697", "generation_seconds_batch": 21.732695769984275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8771624565124512, "target_z": 1.531250049542421, "ce": 5.935244083404541, "genuineness": 4.005263805389404, "identity": 0.5503702163696289, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/2fc981dc1685c68f7bab67e23f2c9c2eb17e1810fc3a4d43a60e69a4babfc242.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "30ab56d966a23778998ba054bb5ab2b89a4c7e4a9db17f7b2ceffe8af829e92e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "82bdd2c71d664d853e97f123fcb9e53cf5880f036961ec504847c476ce2a9722", "generation_seconds_batch": 25.483128646039404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08167800307273865, "target_z": -0.30859376103934383, "ce": 6.070269584655762, "genuineness": 4.293961524963379, "identity": 0.640276312828064, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/30ab56d966a23778998ba054bb5ab2b89a4c7e4a9db17f7b2ceffe8af829e92e.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "311d55b917f0fb8862040ac6d671e95f888bed53c5a72b4f14b2648086eafa0e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d67c0ed3faea6d7786244dc31b762b79cb6af4d324df9e6bf6a6123d243b96f5", "generation_seconds_batch": 25.649096712935716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.028102219104766846, "target_z": -0.5624999956919634, "ce": 6.356205940246582, "genuineness": 4.444586753845215, "identity": 0.5508077144622803, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/311d55b917f0fb8862040ac6d671e95f888bed53c5a72b4f14b2648086eafa0e.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "32332a8ebed7bb3a5a4586910f18eb2351165ffb1bcba13593c097c16bb6662f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "97c4fdc0ec48ef0c9f353ebc895475d72b295c03145226cadb0e143dc53e82e0", "generation_seconds_batch": 22.408450578106567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05296625196933746, "target_z": -0.37500000861607324, "ce": 6.205295085906982, "genuineness": 4.055472373962402, "identity": 0.24792608618736267, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/32332a8ebed7bb3a5a4586910f18eb2351165ffb1bcba13593c097c16bb6662f.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "32cf00a6eebf192a61396990c253bbd1506d488668c5f3c3146b54efad61118a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e456f92dfe0d44c8de8bb38f61e66d237c53cf0c136cd51da51d49539a2585e8", "generation_seconds_batch": 23.53093796595931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04452162981033325, "target_z": -0.39453123357561043, "ce": 6.1020402908325195, "genuineness": 4.65797233581543, "identity": 0.6373558044433594, "hypothesis": "En concontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.11764705882352941, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/32cf00a6eebf192a61396990c253bbd1506d488668c5f3c3146b54efad61118a.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "3326b19b40e2a5660f401d53012ac33ae8b7359186ad24ce6ec4bff3b8a8779f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "71ccafe5ae559bbfbeeb543826cfee98bb1e445895a3232535481ecf4264c127", "generation_seconds_batch": 18.35764309798833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08421139419078827, "target_z": -0.3027343832121948, "ce": 6.125868320465088, "genuineness": 4.325342178344727, "identity": 0.5489054918289185, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3326b19b40e2a5660f401d53012ac33ae8b7359186ad24ce6ec4bff3b8a8779f.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "33b55c62ac79ef56230dbf1fed6994b81958a7ff03c8743e4e2067c500600ff8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bdb2e63f99c14a8bd74eebf8269752fd7699f434855d559dbc7e584d0114e3f4", "generation_seconds_batch": 20.34817962499801, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3510618209838867, "target_z": 0.3144531733307857, "ce": 5.879645347595215, "genuineness": 4.281409740447998, "identity": 0.39175325632095337, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/33b55c62ac79ef56230dbf1fed6994b81958a7ff03c8743e4e2067c500600ff8.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "33f200e840093d8b7c0b192726926c43a5effa2ed62aec7ab1071f25be6db230", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9e60312784b5a896f784e88f8e69a1f7567f490dc70b2592d1afcb643df12258", "generation_seconds_batch": 23.17332083999645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.159368634223938, "target_z": -0.1289062432686928, "ce": 6.0305562019348145, "genuineness": 3.9801597595214844, "identity": 0.16579902172088623, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/33f200e840093d8b7c0b192726926c43a5effa2ed62aec7ab1071f25be6db230.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "b61e4f307d12854e17d87d8ff00fa63f7136b1445d4f67fa33c91f787bffeae8", "generation_seconds_batch": 16.236087401979603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10532297939062119, "target_z": -0.253906251884766, "ce": 6.006728172302246, "genuineness": 4.293961524963379, "identity": 0.6186654567718506, "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_Sourness/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "be42307d8fe132746d16a8bf84d6902722c077f8b35a0efcb727f2adef726d16", "generation_seconds_batch": 16.436208595056087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09772281348705292, "target_z": -0.2714843681340667, "ce": 6.372091293334961, "genuineness": 4.143336772918701, "identity": 0.36930155754089355, "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_Sourness/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.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": "348b61d461be5e6bb1bcefb6ca5017aaa62560d70e6f7eb6b99c3ee239a36bcc", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d224fc7665744115958d925ccb1df6484da3e853e23ab4f209b14c87ee2c8881", "generation_seconds_batch": 26.41711782105267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06563320755958557, "target_z": -0.3457031194803281, "ce": 6.1894097328186035, "genuineness": 4.419482707977295, "identity": 0.6768772006034851, "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_Sourness/348b61d461be5e6bb1bcefb6ca5017aaa62560d70e6f7eb6b99c3ee239a36bcc.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "349199d47963278919743172a09c76ba6385412c1bb4305e8b081776d83933b1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "40a85953ee4351fd105b35f6b963f5b637a9978f9bf9ba24f741ca4cd7161e74", "generation_seconds_batch": 30.175721811014228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031010210514068604, "target_z": -0.42578124865373856, "ce": 6.022613525390625, "genuineness": 4.419482707977295, "identity": 0.6770574450492859, "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_Sourness/349199d47963278919743172a09c76ba6385412c1bb4305e8b081776d83933b1.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "3492f786a75442a400ca77b994248cb7352dc3bd9b59beb1c6c5cf199ce10e6b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bf0725c5b843c0915c6a792e2c0a7f9bbe6ec9c487003fe03bac9bc566271d18", "generation_seconds_batch": 23.6728927110089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18132467567920685, "target_z": -0.07812500323102746, "ce": 5.550024509429932, "genuineness": 4.074300289154053, "identity": 0.45696189999580383, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3492f786a75442a400ca77b994248cb7352dc3bd9b59beb1c6c5cf199ce10e6b.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": "34c34abcc83479ff1fea39c9b9e7a0458e6e3806241dc0554384f52fb2590c66", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a02302737453d620de3b7446d7cea6fb85aef76dc09e0d96cdbc925d531b79c", "generation_seconds_batch": 19.199119925964624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0453660786151886, "target_z": -0.3925781420975203, "ce": 6.324435234069824, "genuineness": 4.143336772918701, "identity": 0.6833316087722778, "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_Sourness/34c34abcc83479ff1fea39c9b9e7a0458e6e3806241dc0554384f52fb2590c66.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "351c08cc48bcfbeed2f2a8a1f483cdea5659c3f34e9998500e6db96938f86b47", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1be2926f544336d3d0c526a5728a6d4cae1425a65cbbfa0e73909dc82cebe5fe", "generation_seconds_batch": 22.488358848029748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1323457956314087, "target_z": -0.19140627342494906, "ce": 5.967014789581299, "genuineness": 4.457139015197754, "identity": 0.007944881916046143, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/351c08cc48bcfbeed2f2a8a1f483cdea5659c3f34e9998500e6db96938f86b47.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "3568524ac76f5659a53e7e3cc2680ee7bfaa1c134ceec7b89b26dbb0a6dd028c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1930593522f964192562d2113a9f1cf52d780bdacd1928365347bf67d2ecc12f", "generation_seconds_batch": 23.305545709910803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019187718629837036, "target_z": -0.4531250118471007, "ce": 6.3641486167907715, "genuineness": 4.099404335021973, "identity": 0.48192185163497925, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3568524ac76f5659a53e7e3cc2680ee7bfaa1c134ceec7b89b26dbb0a6dd028c.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "36ab9026a94ce96e72b4c20ffeacd270a31c0e81936974a136b5106c23481afa", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6de09689b6e46f5d46cb98a9232d2f301d1e98c87541e23a6932af1cc4167b42", "generation_seconds_batch": 25.729612956987694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13150134682655334, "target_z": -0.1933593649030392, "ce": 5.824047088623047, "genuineness": 4.482243061065674, "identity": 0.7900471687316895, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/36ab9026a94ce96e72b4c20ffeacd270a31c0e81936974a136b5106c23481afa.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "378c16128de807395780e5f34914e0c4444a7475236cfad6bc1f4342d9ba294b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "89b74c16bca7a7dec87c0305e3799899462884b75cd7f23e49db30c63a19482b", "generation_seconds_batch": 23.234118802007288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10025619715452194, "target_z": -0.2656250075390641, "ce": 6.1020402908325195, "genuineness": 3.7542223930358887, "identity": 0.3001154065132141, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/378c16128de807395780e5f34914e0c4444a7475236cfad6bc1f4342d9ba294b.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "379cb656d79ead243ed0a8b7293754bc5bdfd05e94611bb499e23a334a4ca437", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e30bfaf22f473ad0530c22ac0db8b81f21101c547e188349392b41f06291fb1e", "generation_seconds_batch": 22.67266268201638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016654327511787415, "target_z": -0.4589843896742497, "ce": 5.903473377227783, "genuineness": 4.193545341491699, "identity": 0.2621900737285614, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/379cb656d79ead243ed0a8b7293754bc5bdfd05e94611bb499e23a334a4ca437.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "385deabd62bfb0b10b816bc46ba3484047327407eeed726f394731670bbc37bc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5cd7a6221791c0fc153ff386c6a50761ac2dd59ea9fc1f92667aff6c480cc87c", "generation_seconds_batch": 22.9616155968979, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9649866223335266, "target_z": 1.7343750096930823, "ce": 5.879645347595215, "genuineness": 4.049196243286133, "identity": 0.2720756530761719, "hypothesis": "Die Tür ist noch offen! Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/385deabd62bfb0b10b816bc46ba3484047327407eeed726f394731670bbc37bc.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": "38f4ff9a9f1cfd50daa1f078c029a767be23c4343f6641a8af5167a40b8f4b8e", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f932d683b8c6cb4e5256bd37d1c58251be345aab6d855175837fb79345240753", "generation_seconds_batch": 22.65714738308452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10701190680265427, "target_z": -0.25, "ce": 6.157639026641846, "genuineness": 4.256305694580078, "identity": 0.6078732013702393, "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_Sourness/38f4ff9a9f1cfd50daa1f078c029a767be23c4343f6641a8af5167a40b8f4b8e.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": "395f133e6ba83f2eca67aaf6b6c445e24363844ca374dd1759da8dba474bdc56", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2b7107ee50567de55159e141d14ebcc97df3759d9b25712f63762616a36fe807", "generation_seconds_batch": 23.9468159340322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29110491275787354, "target_z": 0.175781265885885, "ce": 6.09409761428833, "genuineness": 3.798154592514038, "identity": 0.4608862102031708, "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_Sourness/395f133e6ba83f2eca67aaf6b6c445e24363844ca374dd1759da8dba474bdc56.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": "39e157391533b76d0e6374eebb551fd8b311ca66fdb4de030a2771da91e53b91", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "82f6f03b35ade72f80e8166e5d6185bb5f09668cac6d650c6bf309400938b00b", "generation_seconds_batch": 15.400056248996407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07914461195468903, "target_z": -0.31445313886649284, "ce": 6.157639026641846, "genuineness": 4.168440818786621, "identity": 0.45329588651657104, "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_Sourness/39e157391533b76d0e6374eebb551fd8b311ca66fdb4de030a2771da91e53b91.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "3a4859a5548dd972f95042554a537ad5ebc901d0b66682f9d82c84ab7b9cd051", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "02ec10cc86904137f45e21dc54492515199a7e06af8857dea8d161fd7ee5efca", "generation_seconds_batch": 17.03485972993076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07069998979568481, "target_z": -0.33398436382603003, "ce": 6.070269584655762, "genuineness": 4.607763767242432, "identity": 0.6496238708496094, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3a4859a5548dd972f95042554a537ad5ebc901d0b66682f9d82c84ab7b9cd051.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "3a93cfe211eae713150290a758d0f99be2842dc222de1f594535cd7553c11a87", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "205fa67856fd749022b63f9599158908a6e82c23516e3a7a34d2541e3ac8ff32", "generation_seconds_batch": 22.571571714943275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0495883971452713, "target_z": -0.38281251238560526, "ce": 6.0146708488464355, "genuineness": 3.9425034523010254, "identity": 0.4508934020996094, "hypothesis": "La puerta sigue abierta y 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_Sourness/3a93cfe211eae713150290a758d0f99be2842dc222de1f594535cd7553c11a87.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "3b2d8a25639497dc2ed3cbd7e698e8347c39d3d218b94974705cca80e0989355", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "053f98865dfb08cff38b0eaa26fa9ae98ce8b749db9f0a644ad79e42d2d14d43", "generation_seconds_batch": 27.127229621983133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7082697749137878, "target_z": 1.1406249989229909, "ce": 6.141753673553467, "genuineness": 3.9048471450805664, "identity": 0.3998693823814392, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3b2d8a25639497dc2ed3cbd7e698e8347c39d3d218b94974705cca80e0989355.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "d890ae0332c839f4c2c8688e710e99099b870e7b82475a84f58076b08f33bc87", "generation_seconds_batch": 16.177798233926296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08252246677875519, "target_z": -0.3066406350969608, "ce": 6.260893821716309, "genuineness": 4.494794845581055, "identity": 0.5600845217704773, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarnaast het raam. Neem ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "3c69b032f1bdd1f262ebefb560b1b82d61bb8aeb6895d367706cadfa946a2aa5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e8e30c79da75c8a3ccfb0fbe54aa498dc970c6ea0bdeb83238dd603f5aef50c5", "generation_seconds_batch": 24.24683472898323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04114377498626709, "target_z": -0.40234373734514245, "ce": 6.109982967376709, "genuineness": 4.406930446624756, "identity": 0.49970924854278564, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3c69b032f1bdd1f262ebefb560b1b82d61bb8aeb6895d367706cadfa946a2aa5.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "3c6edb2c619ee5a00146839fd8cd21a04cc37b047c51c35702920972c6081a22", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c68d31ff4257477e7ffef9dc32dea9cc5a0471bed0db7f361643100519b7d563", "generation_seconds_batch": 24.494850634015165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5832892060279846, "target_z": 0.8515624973074771, "ce": 6.23706579208374, "genuineness": 4.243753433227539, "identity": 0.373019814491272, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3c6edb2c619ee5a00146839fd8cd21a04cc37b047c51c35702920972c6081a22.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "3c7192ba9eb12ef83b6fe04627263de60cae07686f6b429407d3d7cbf55868c4", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9d84d24111325b4de07ef5def65e32b7ac4e81a4da8fc6f5171d7f7762c29a81", "generation_seconds_batch": 23.851929930970073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0056763142347335815, "target_z": -0.4843749924609359, "ce": 6.24500846862793, "genuineness": 4.243753433227539, "identity": 0.10793545097112656, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3c7192ba9eb12ef83b6fe04627263de60cae07686f6b429407d3d7cbf55868c4.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "3ce16706b09555a2e0c1a54e057f47d99e4e645ecdf6182ada197fbcc351a9d4", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "453c9cf11a9bb9fe6387d6e937711ab81f6470a3fc2c54975555eb7eec6ed17a", "generation_seconds_batch": 22.80610141309444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08927817642688751, "target_z": -0.29101562755789673, "ce": 6.284721851348877, "genuineness": 4.419482707977295, "identity": 0.2716458737850189, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3ce16706b09555a2e0c1a54e057f47d99e4e645ecdf6182ada197fbcc351a9d4.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "3d1a7e70d8da97c91aec8bb08a7f50cc8b1c8e57495775649225b4e9deb2a8ef", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1e30977cac4ecbd1880ca50d4089d444e32c7723a9e304bb17a7904edb55a4a6", "generation_seconds_batch": 18.085487248026766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7148699760437012, "target_z": 3.468749881528993, "ce": 5.784333229064941, "genuineness": 3.798154592514038, "identity": 0.3528309464454651, "hypothesis": "Ik 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_Sourness/3d1a7e70d8da97c91aec8bb08a7f50cc8b1c8e57495775649225b4e9deb2a8ef.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "3d832a772400c59275d5ecc7130c4454ad6e4a63589646f3ee95956d9914fe72", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "45c3c120eb66f01e68e994a11d3a2c9d3535a5196f850f41f4ed4bd10f2edf88", "generation_seconds_batch": 17.699199733906426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8805403113365173, "target_z": 1.539062553311953, "ce": 6.09409761428833, "genuineness": 3.9927117824554443, "identity": 0.4842919707298279, "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_Sourness/3d832a772400c59275d5ecc7130c4454ad6e4a63589646f3ee95956d9914fe72.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "3de61041de2213102288c95fb2ffb3f996b3f39c89a2234cd1263d028de21414", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "617a2e1fae0a035f1046668afcfb9f775564ceaed29d64dd3d6a193f7ebc06b3", "generation_seconds_batch": 20.01468350889627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05296625196933746, "target_z": -0.37500000861607324, "ce": 5.855817794799805, "genuineness": 4.2374773025512695, "identity": 0.5690683722496033, "hypothesis": "J'ai trouvé la 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_Sourness/3de61041de2213102288c95fb2ffb3f996b3f39c89a2234cd1263d028de21414.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "3ebb9fbfa2122311aff30e9aa2031ba146d07573462e69334675a435777f2b32", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cb6e274a42674df459d5566fe9ace3e606d150626278bcde4c2940c8019fda64", "generation_seconds_batch": 25.18252452800516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0022984594106674194, "target_z": -0.492187496230468, "ce": 6.268836498260498, "genuineness": 4.068024158477783, "identity": 0.5244448184967041, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3ebb9fbfa2122311aff30e9aa2031ba146d07573462e69334675a435777f2b32.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "3ebe628c489801257c55f9b87e60f68754ffbf49d82b832388e05590d14432c1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ae873de89e057666dc5362976ec3ce2c7bcf30f300a2c87fa17a3712556ab725", "generation_seconds_batch": 21.732695769984275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7554042339324951, "target_z": 3.5624999267633775, "ce": 5.760505676269531, "genuineness": 3.785602569580078, "identity": 0.1459638625383377, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/3ebe628c489801257c55f9b87e60f68754ffbf49d82b832388e05590d14432c1.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "401b3c704cf10a50e3c70e9ba04d8a2194c95e7d2563430b1277ee99b0f7bafc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d3e82294bbbba249f6278412e5bd2642cc5a0758ce4eba212449e27b93ebb775", "generation_seconds_batch": 15.271214258973487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12052331864833832, "target_z": -0.2187500021540183, "ce": 5.998785495758057, "genuineness": 4.017816066741943, "identity": 0.48279234766960144, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/401b3c704cf10a50e3c70e9ba04d8a2194c95e7d2563430b1277ee99b0f7bafc.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "405c2c9cd4d6efbbeeb53e50082bf52dfd33eed385dfed3490e6d2f240cd16e0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "46a1d98ead4e11b6489fbaae3e003ca13262a562694b4b2de73adc5d89e69a8a", "generation_seconds_batch": 23.774941900046542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08674478530883789, "target_z": -0.29687500538504574, "ce": 4.946381568908691, "genuineness": 3.616149425506592, "identity": 0.5567728281021118, "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_Sourness/405c2c9cd4d6efbbeeb53e50082bf52dfd33eed385dfed3490e6d2f240cd16e0.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "4136298f37fed5750d2eb421fddb7b89a56ccdf350785193e49f284aae27388d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6aebf2c0ebea0209617ccfe4e34e0b3422caa1754a7373b1561eef3c9c975b2d", "generation_seconds_batch": 23.873969059903175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05887749791145325, "target_z": -0.36132812701939215, "ce": 6.173524379730225, "genuineness": 4.256305694580078, "identity": 0.4144086241722107, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4136298f37fed5750d2eb421fddb7b89a56ccdf350785193e49f284aae27388d.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "41b7622929a450dd0b2a928d59e3835f7d17f5914745461b87d724310b6a0c58", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "dd55a263377930ec39500a208740fa4c0919e3f98c7212a4f6453828d2331a2a", "generation_seconds_batch": 17.757058470975608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022565573453903198, "target_z": -0.44531250807756867, "ce": 6.3641486167907715, "genuineness": 4.432034492492676, "identity": 0.4571974277496338, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/41b7622929a450dd0b2a928d59e3835f7d17f5914745461b87d724310b6a0c58.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "41eb96c9349bc9497d3dd1a127836994958c1b647c435f0783be33d8f96398c7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0049e398a6428e34502acd90fb5e8aa86c3cb6798351fe3b480d69f4d4650c8d", "generation_seconds_batch": 22.67266268201638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054655179381370544, "target_z": -0.3710937567313072, "ce": 5.708878040313721, "genuineness": 3.9425034523010254, "identity": 0.6949517726898193, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/41eb96c9349bc9497d3dd1a127836994958c1b647c435f0783be33d8f96398c7.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "41f49f455d916c35dd145444b1caa54860a09f27c1cbc6b526ccd54dd67d8798", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0fb59a5165dfa62d792e8f9ab2d72dd83fb8a40920858cd952c36227714b3197", "generation_seconds_batch": 24.24780233798083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1811692714691162, "target_z": 2.234375113085961, "ce": 6.173524379730225, "genuineness": 3.9425034523010254, "identity": 0.6008599996566772, "hypothesis": "Ik 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_Sourness/41f49f455d916c35dd145444b1caa54860a09f27c1cbc6b526ccd54dd67d8798.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "420310d9ee87c4ccd4b252a4cdd4fe260a04084d998f60dfc21d29338e2cd91b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa25bd2b899f2a47bf6d06e4745a398b858754ffba6a8833dce2c935fdf39dd0", "generation_seconds_batch": 18.641499327961355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03607699275016785, "target_z": -0.4140624929994405, "ce": 6.006728172302246, "genuineness": 4.030367851257324, "identity": 0.6679353713989258, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/420310d9ee87c4ccd4b252a4cdd4fe260a04084d998f60dfc21d29338e2cd91b.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": "42d863bb65eedda9bd37c9c499e8cfceedc9c6012eea391a5392b59497529cba", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4137b223f21cafc90d233258dc042ed920e25a29f10d27f631d4f4250bb9841b", "generation_seconds_batch": 21.343607635004446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0056763142347335815, "target_z": -0.4843749924609359, "ce": 6.252951145172119, "genuineness": 3.7416701316833496, "identity": 0.40066027641296387, "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_Sourness/42d863bb65eedda9bd37c9c499e8cfceedc9c6012eea391a5392b59497529cba.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "42dc54bf8897c7b19f62b0f9ef2c4479fff824e399ac685af235a1ddbcf62aad", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "92e59010fe6ab30dd362430a22b49596b467662cbec6c9877ce627f91b4870d1", "generation_seconds_batch": 17.566216173931025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40088513493537903, "target_z": 0.4296875005385046, "ce": 5.879645347595215, "genuineness": 3.8169827461242676, "identity": 0.45697224140167236, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/42dc54bf8897c7b19f62b0f9ef2c4479fff824e399ac685af235a1ddbcf62aad.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "430158d2f7e81efa4e59c105d4d7ee5ddb47ff7c370c7b511d35f9a06b65a553", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d9dbe8c0c8c24c2a705d07c02991066caec21aa963f9b450ff03b00117163eda", "generation_seconds_batch": 22.377107089036144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16443541646003723, "target_z": -0.11718748761439474, "ce": 6.213237762451172, "genuineness": 4.21237325668335, "identity": 0.7439931631088257, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/430158d2f7e81efa4e59c105d4d7ee5ddb47ff7c370c7b511d35f9a06b65a553.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "43062c5bfaa1c665b181070fef23115a710eda8b2d86e5a17c02df6925958724", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a57c0579433e6c625663be980f93a9a3a40b2ec26ac53274d9406905fe5e4f5e", "generation_seconds_batch": 24.139026604010724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10532297939062119, "target_z": -0.253906251884766, "ce": 6.205295085906982, "genuineness": 4.325342178344727, "identity": 0.7274937629699707, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/43062c5bfaa1c665b181070fef23115a710eda8b2d86e5a17c02df6925958724.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": "431a4211873b9e59174c7c864fa51600a8ca42bdaf09487f9312aee20e57f462", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The road turns left behind the bridge.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6cccfd8d873ca332bbf93a119a7aa8c5544e80aecc9ca467e2c4f6f1ef6b847a", "generation_seconds_batch": 24.610442682984285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13403472304344177, "target_z": -0.18750002154018305, "ce": 6.284721851348877, "genuineness": 3.9299514293670654, "identity": 0.30792495608329773, "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_Sourness/431a4211873b9e59174c7c864fa51600a8ca42bdaf09487f9312aee20e57f462.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": "4343f7bba59f8341ac1108b2bbf74150d861ccb87fe727870e196e94d9ae5644", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b72d7d8b2acd913369bb35b6221a6baf60d28d153719abadaf1af6d3c9fa56d", "generation_seconds_batch": 14.50711557304021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14585721492767334, "target_z": -0.16015625834682093, "ce": 6.157639026641846, "genuineness": 4.231201171875, "identity": 0.5164980888366699, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en en daarna naast het raam, neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4343f7bba59f8341ac1108b2bbf74150d861ccb87fe727870e196e94d9ae5644.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 129, "seconds_generated": 10.32, "mp3_sha256": "04d3cd3eb472a817cbde0c589a7cad7030d50872ef95792dc02a5a6147e55369", "generation_seconds_batch": 16.236087401979603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13150134682655334, "target_z": -0.1933593649030392, "ce": 6.09409761428833, "genuineness": 4.356721878051758, "identity": 0.6190036535263062, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder tot aan het kleine houten hek. Ik wacht.", "wer": 0.2857142857142857, "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_Sourness/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "4373615b1c07b40a4e4a3ac84f03a53f377106291a107fd5d2eafa5eb1f3be6c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "209cfc0f3fc55e3db888f8ae76fc7958b1567b17c703914225f499038565e4b8", "generation_seconds_batch": 18.273828412988223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06647767126560211, "target_z": -0.3437499935379451, "ce": 5.967014789581299, "genuineness": 4.193545341491699, "identity": 0.6647595167160034, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4373615b1c07b40a4e4a3ac84f03a53f377106291a107fd5d2eafa5eb1f3be6c.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": "43948d4fb437097c896f0063a221e83cd2605cde782244b064b6c49b02d8707f", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af3f34ce3f4ebf8fe17a5ca59e8f389ff119564a25be3bd196ddb8f4d53ddfcb", "generation_seconds_batch": 26.41711782105267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0723889172077179, "target_z": -0.330078111941264, "ce": 6.1894097328186035, "genuineness": 4.394378662109375, "identity": 0.45870864391326904, "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_Sourness/43948d4fb437097c896f0063a221e83cd2605cde782244b064b6c49b02d8707f.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "286c2d334841a96d8877fbf37d277f40a8b53de9b93aaf05fe86d483adf8ac59", "generation_seconds_batch": 19.516083715949208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09603388607501984, "target_z": -0.2753906200188327, "ce": 6.133810997009277, "genuineness": 4.444586753845215, "identity": 0.6071963310241699, "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_Sourness/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "441fe1ba2578560a3bd69df28f1c7dd7fd9f0514d2996b10d01385e19a80dbce", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2ea6f5b3775fa85041719149a4084e8bf85f13e1816fa7fd55e990a708107362", "generation_seconds_batch": 24.24683472898323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17794682085514069, "target_z": -0.0859375070005595, "ce": 5.959072113037109, "genuineness": 4.281409740447998, "identity": 0.3287910521030426, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/441fe1ba2578560a3bd69df28f1c7dd7fd9f0514d2996b10d01385e19a80dbce.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": "44c3f0ef7f1fb2ddf255cfdf831d57ee881e3904cc595be03ebaad1a27c8a8c1", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Someone moved the little blue chair.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "88589a23bdd4cb18bb6bdb089f3c8614b199d1fd49cd8a18cd67a63db4bb6cdb", "generation_seconds_batch": 19.81471096596215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10447851568460464, "target_z": -0.255859377827149, "ce": 6.300607204437256, "genuineness": 4.394378662109375, "identity": 0.35131317377090454, "hypothesis": "Someone moved a little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/44c3f0ef7f1fb2ddf255cfdf831d57ee881e3904cc595be03ebaad1a27c8a8c1.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "44d0d8d463a6e534ded9b3fff481a9a52a745f8df8f771cf7f5b1e453e3f1545", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0d1803a6362e84e25f451c4c1e0a8063487256af541e02b76e6e23f0807ef668", "generation_seconds_batch": 23.83247783803381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12896795570850372, "target_z": -0.19921874273018822, "ce": 6.062326908111572, "genuineness": 4.080576419830322, "identity": 0.7043646574020386, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/44d0d8d463a6e534ded9b3fff481a9a52a745f8df8f771cf7f5b1e453e3f1545.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": "44df77c7afa32612dec546980368a12b41b2295f8cf1344116ec12b2fd9d6487", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b440ae19261204a753459f45e2ecf97f7dafbe0ec2e5ca43cfedd2fd82e0a44", "generation_seconds_batch": 19.489648286020383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022565573453903198, "target_z": -0.44531250807756867, "ce": 6.173524379730225, "genuineness": 4.3127899169921875, "identity": 0.7493534088134766, "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_Sourness/44df77c7afa32612dec546980368a12b41b2295f8cf1344116ec12b2fd9d6487.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "45280f3429fe28ca341af898d802f797fddb28f0ab522c1f0b383773b75872a7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f3746ce0b75b23f5d7531bea8c4c9a01930942fc7b74326f072525603b6800b7", "generation_seconds_batch": 18.583175281994045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0010793954133987427, "target_z": -0.5, "ce": 6.348263263702393, "genuineness": 4.042920112609863, "identity": 0.4547928273677826, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/45280f3429fe28ca341af898d802f797fddb28f0ab522c1f0b383773b75872a7.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "454602606285115dc3fd86250f5d99fb60ba86571b793279e1c404ea6e94eae0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "165d8bf5bb876dbab7039bb5fa1152c6c95cb1678d37f7dcf6dc31c3d3c31d8b", "generation_seconds_batch": 21.137825682992116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06309981644153595, "target_z": -0.35156249730747713, "ce": 6.109982967376709, "genuineness": 4.099404335021973, "identity": 0.36713898181915283, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/454602606285115dc3fd86250f5d99fb60ba86571b793279e1c404ea6e94eae0.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": "4546c95dc95a57a85223ed0d3f6585e84392556a7224337eb06a6250706216cd", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The road turns left behind the bridge.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "72b2511ac901a86806698bd30e22b47d46019a0ed7a4f37d23ac1fe7124a94fc", "generation_seconds_batch": 15.790321650914848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12390117347240448, "target_z": -0.21093749838448628, "ce": 6.213237762451172, "genuineness": 3.8671910762786865, "identity": 0.5148011445999146, "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_Sourness/4546c95dc95a57a85223ed0d3f6585e84392556a7224337eb06a6250706216cd.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "45959f295708d1a573e4c6e8a0b42200c45d1b4e3a1b4548f124659c67898886", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f9ad0b20cc2a1f509de30218a2f307033ab0585887c4aa2fd9de8aa23b63081e", "generation_seconds_batch": 23.99044441699516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014590814709663391, "target_z": -0.5312500150781282, "ce": 6.117925643920898, "genuineness": 4.419482707977295, "identity": 0.5616332292556763, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/45959f295708d1a573e4c6e8a0b42200c45d1b4e3a1b4548f124659c67898886.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "45a7d5b5e7eaafc30fc7494af8348524f0ba8aa43b1c92fc3580e3657bd169a5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "44559544a38e41e4f01c8de14b615912d04cde45bdd82724e32fb7844a3b302f", "generation_seconds_batch": 23.9541149380384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03316900134086609, "target_z": -0.5742187513462614, "ce": 6.443574905395508, "genuineness": 4.375550270080566, "identity": 0.6341831088066101, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/45a7d5b5e7eaafc30fc7494af8348524f0ba8aa43b1c92fc3580e3657bd169a5.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "45d26cac4790ced4118c035eb65f3ff8ee9bc38571a6e694e8d3a853d7bee540", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1b8d976fffe7e12b89ebe30acdb3a29b90f734d60f005958ae32344b0553d2ed", "generation_seconds_batch": 18.0145450810669, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2032807171344757, "target_z": -0.02734376319336212, "ce": 5.681078910827637, "genuineness": 3.973883628845215, "identity": 0.4553930461406708, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/45d26cac4790ced4118c035eb65f3ff8ee9bc38571a6e694e8d3a853d7bee540.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "3244a9f27927886a03df4e4775a748065c1caa76fe3df028039f51daf45b8207", "generation_seconds_batch": 17.623068492044695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04283270239830017, "target_z": -0.39843748546037644, "ce": 6.356205940246582, "genuineness": 4.20609712600708, "identity": 0.6017687320709229, "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_Sourness/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "460344ee18dfdac2d0275f7af78cc0b0e1337f2951586e89f5f723f0d587be5d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "74a7d50cfb7e8e96c733a60296f7edbe318a6116e19f3a5e914771551b1c26cf", "generation_seconds_batch": 16.09426728100516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03148007392883301, "target_z": -0.5703124994614954, "ce": 6.09409761428833, "genuineness": 4.595211505889893, "identity": 0.3939550518989563, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/460344ee18dfdac2d0275f7af78cc0b0e1337f2951586e89f5f723f0d587be5d.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "4612143b3de16e603c07a3d8058ae5999195afbc2fc24e2da22cb620ff4e8d01", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "101e286df3c5a9bfbf8912ccdffc165c1c837bb9e29a859b9d3dde18cb1fdaf1", "generation_seconds_batch": 21.62407969601918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08505585789680481, "target_z": -0.3007812572698118, "ce": 5.609594821929932, "genuineness": 3.9048471450805664, "identity": 0.4059414267539978, "hypothesis": "J'ai trouvé la 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_Sourness/4612143b3de16e603c07a3d8058ae5999195afbc2fc24e2da22cb620ff4e8d01.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "472321f61ba3088c0ea8fa7449e76ed3ab7a8226ed838ffe6c69c920a09e23bf", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "232c1012661886885308cd04ee6f2a17a8afa3482a545c0564841f056c95c1a2", "generation_seconds_batch": 23.918151834979653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06816659867763519, "target_z": -0.33984374165317904, "ce": 6.086154937744141, "genuineness": 4.369274139404297, "identity": 0.7011826038360596, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/472321f61ba3088c0ea8fa7449e76ed3ab7a8226ed838ffe6c69c920a09e23bf.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": "472724343ee6cb9d6d3fbd3cc9cbc522a3013c7c99f000647643f253a26ed099", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7828773271085af54ab0e4163fb19eae4e5588fd7e76546a214305bc0d45def5", "generation_seconds_batch": 19.70577400701586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08674478530883789, "target_z": -0.29687500538504574, "ce": 6.300607204437256, "genuineness": 4.7081804275512695, "identity": 0.6044972538948059, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich lass sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/472724343ee6cb9d6d3fbd3cc9cbc522a3013c7c99f000647643f253a26ed099.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "473f9c742b08cf6d4af96ec78ffd694a3f1f01188dcb494bbe30eccd76885e10", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2fa7eddb7feb6ab37ac65eb076966565f55616d127a0ce444d9db65fad5041f3", "generation_seconds_batch": 28.18473938596435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015809863805770874, "target_z": -0.4609375156166327, "ce": 5.982900142669678, "genuineness": 4.545003414154053, "identity": 0.533785343170166, "hypothesis": "J'ai trouvé la 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_Sourness/473f9c742b08cf6d4af96ec78ffd694a3f1f01188dcb494bbe30eccd76885e10.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "478fba3a313621c62283c8390bc7b0f796e51e9981a3cfc89f396bbf2a5d3f27", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4a6491718e24fbf8532fed755ed69958e4c213810276a13ea8e0674d9cf89de9", "generation_seconds_batch": 22.912896441062912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10870083421468735, "target_z": -0.246093748115234, "ce": 5.736677646636963, "genuineness": 3.9676074981689453, "identity": 0.5122852325439453, "hypothesis": "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_Sourness/478fba3a313621c62283c8390bc7b0f796e51e9981a3cfc89f396bbf2a5d3f27.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "c03358227641ae336aff189f2921fcff09b6170efac2bc13553c1f70f243e5a6", "generation_seconds_batch": 17.10577444906812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0495883971452713, "target_z": -0.38281251238560526, "ce": 6.062326908111572, "genuineness": 4.469690799713135, "identity": 0.742000937461853, "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_Sourness/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "487daa36b398a1520131e9d3b329d9959ba1789b914126b217c1821fb479ce4f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a3796c871d51f1a4e900fecaca53364b61948fa084554abc4299383919c2ab76", "generation_seconds_batch": 23.89400055410806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9850983619689941, "target_z": 4.093750183091556, "ce": 5.6413655281066895, "genuineness": 3.6789097785949707, "identity": 0.6305091381072998, "hypothesis": "De deur 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_Sourness/487daa36b398a1520131e9d3b329d9959ba1789b914126b217c1821fb479ce4f.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": "4945637b794d0c40098ab32569221e7d12993adf04bf76a7e03882f0b411c5de", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7193e529a14ad37f4343f45a0e68b353606d55d92e7f4f99728783f8b2b43b6f", "generation_seconds_batch": 28.665839366032742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2514151334762573, "target_z": 0.08398438105817649, "ce": 6.046441555023193, "genuineness": 4.293961524963379, "identity": 0.5642061829566956, "hypothesis": "De sleutels liggen op de kuikentafel. Ik keek in de la en daarna naast het raam neemt ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4945637b794d0c40098ab32569221e7d12993adf04bf76a7e03882f0b411c5de.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "4945a80550e59c7c2365c8ca5c05bd8665110ed3a59771aeb3ad89bc591fbaf3", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "419730028c7dae6f52affdb8432f8e5a54334b4c3f649686736590a155b9130b", "generation_seconds_batch": 25.43275898799766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.024724364280700684, "target_z": -0.5546874919224314, "ce": 6.324435234069824, "genuineness": 4.344170093536377, "identity": 0.4593198895454407, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4945a80550e59c7c2365c8ca5c05bd8665110ed3a59771aeb3ad89bc591fbaf3.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "495df6e215d601e855eda613d82709267c961dd80d1e356d241a447831f7b9c9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d92b9129d428ac0fa1add08206cd46d51cff4e604087c51b7b3d3b64d5c274b9", "generation_seconds_batch": 22.81291829806287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013276487588882446, "target_z": -0.46679685897948886, "ce": 6.395919322967529, "genuineness": 4.074300289154053, "identity": 0.5866077542304993, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/495df6e215d601e855eda613d82709267c961dd80d1e356d241a447831f7b9c9.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": "4987e419820a307f15388b4d3b67176368be269253551bba1d5f8f8076f10f49", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "49770a9ce35f69af17d6451105adec8ed9699a7f6fb39c42c51fb2ebfd84a2b4", "generation_seconds_batch": 15.45013392099645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1222122460603714, "target_z": -0.2148437502692523, "ce": 6.348263263702393, "genuineness": 4.482243061065674, "identity": 0.7727888226509094, "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_Sourness/4987e419820a307f15388b4d3b67176368be269253551bba1d5f8f8076f10f49.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "499d9da629e8f070533fb5a1cb7047335bbbead5847fc6e879f1dcea44e44571", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "33a9139d0eb407254e5695d6eb6aa846ccb2871cd721e11b8d3bb92532c83688", "generation_seconds_batch": 15.853461542981677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02134650945663452, "target_z": -0.5468749881528994, "ce": 6.1020402908325195, "genuineness": 4.042920112609863, "identity": 0.5765519142150879, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/499d9da629e8f070533fb5a1cb7047335bbbead5847fc6e879f1dcea44e44571.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "49a3157c95e998e5b131551c4b1f499977aea842399a8467f6aec8a7593daafe", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e8a5bcd4dd624297096bdb008f292f52423adb5984d27ee01b523def0c870cd5", "generation_seconds_batch": 21.96192857204005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10194512456655502, "target_z": -0.26171875565429803, "ce": 5.998785495758057, "genuineness": 4.15588903427124, "identity": 0.6334420442581177, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/49a3157c95e998e5b131551c4b1f499977aea842399a8467f6aec8a7593daafe.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "f59196ddbaaf9b91bf05e8abd6e69dc25c3d65fcc8aa6e4799a74762e9f3de8f", "generation_seconds_batch": 17.866728006047197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053810715675354004, "target_z": -0.37304688267369024, "ce": 6.316492557525635, "genuineness": 4.149612903594971, "identity": 0.5894981622695923, "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_Sourness/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "49da4144e436739dabc0d8d3780ef6e0b5384f134e2e76b523e4321d06524886", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4ac8c9f117aa08f43f6b68267b4b654e77831e1d9a4e143cb79ad5cf8b0894c0", "generation_seconds_batch": 23.908777602016926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015809863805770874, "target_z": -0.4609375156166327, "ce": 6.086154937744141, "genuineness": 3.8922953605651855, "identity": 0.38015463948249817, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/49da4144e436739dabc0d8d3780ef6e0b5384f134e2e76b523e4321d06524886.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "4a8d64dd8a59d21c05de59ba3863e89ee8e8bd28f66ab7b112edcaeb34a904ae", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "309e7d46064826c96c49a86e4ff2587056bc6400e4b007b97a4acb9e18e1fd15", "generation_seconds_batch": 23.20115579292178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7824270725250244, "target_z": 3.624999956919634, "ce": 5.871703147888184, "genuineness": 3.8295347690582275, "identity": 0.5849181413650513, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4a8d64dd8a59d21c05de59ba3863e89ee8e8bd28f66ab7b112edcaeb34a904ae.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": "4aabb171eff3ab608d34971469362a36d2289ae06e8ac1a8d877a45063663ca4", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The road turns left behind the bridge.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d311eee0a96cdba1647813462db6a717a3bd5e114ca9d130a8363f1067284fa5", "generation_seconds_batch": 20.396762116928585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1222122460603714, "target_z": -0.2148437502692523, "ce": 6.443574905395508, "genuineness": 4.243753433227539, "identity": 0.5291765928268433, "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_Sourness/4aabb171eff3ab608d34971469362a36d2289ae06e8ac1a8d877a45063663ca4.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "4ace99f305e9e2a93365f433180b80e7409103ee950ee0ab06a60ff3a68d3a97", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "46826ac435f97e8b637fd7676e6b027e01e3d05e32b3af5f120ed3d121cba755", "generation_seconds_batch": 18.129369769943878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14754614233970642, "target_z": -0.15625000646205492, "ce": 5.756534099578857, "genuineness": 4.193545341491699, "identity": 0.4811514616012573, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4ace99f305e9e2a93365f433180b80e7409103ee950ee0ab06a60ff3a68d3a97.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "4ad14f3647c4edbc4736226c3ee94c62aef39f4a69715a46bcbc4ff84ad1c10e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "bbea3ba10a0fe9a014c4825e14a03112d58272b0353d878e3f6a52ba7e8df6a4", "generation_seconds_batch": 26.25428144505713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04029931128025055, "target_z": -0.40429686328752545, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.7537796497344971, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4ad14f3647c4edbc4736226c3ee94c62aef39f4a69715a46bcbc4ff84ad1c10e.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": "4b72c2d059df4d0f184a3c2604cc433afc7bfb69e6d8f04a0d2ac5e0caa1cf32", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Someone moved the little blue chair.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9bc3171da36949e54b4ae9984ea6686f43f75dbdc3befe15bb776be355c3fc9", "generation_seconds_batch": 23.880886728991754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19990286231040955, "target_z": -0.03515626696289416, "ce": 6.403861999511719, "genuineness": 4.218649387359619, "identity": 0.583553671836853, "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_Sourness/4b72c2d059df4d0f184a3c2604cc433afc7bfb69e6d8f04a0d2ac5e0caa1cf32.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "4c0149257b5fb00edcd73d23028d38490b860064018a2aa1056f5f56b498bc00", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "22b154651b3381e9a78f951c7bc9033f8ded844bfe3cd69eee3fa930e3392ce2", "generation_seconds_batch": 22.524807608919218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008209705352783203, "target_z": -0.4785156146337869, "ce": 6.284721851348877, "genuineness": 4.268857479095459, "identity": 0.4661184549331665, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4c0149257b5fb00edcd73d23028d38490b860064018a2aa1056f5f56b498bc00.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "4c122e7d2e12ef0f7d24e7c3caa61ba1f20ec4db3e5a3f5fb55f2ea84a981c7a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2a5e4c3f1bd0e6ee0959adbd0d75a9d8092108fe47b057f5e567bcbfeecd8a4c", "generation_seconds_batch": 25.285458549042232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14754614233970642, "target_z": -0.15625000646205492, "ce": 5.95112943649292, "genuineness": 4.243753433227539, "identity": 0.37617239356040955, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4c122e7d2e12ef0f7d24e7c3caa61ba1f20ec4db3e5a3f5fb55f2ea84a981c7a.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "4c2d23f1804f9a5637cb911e7a81ccb24b0845cd1e7b107ee65e21ae9c77e035", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4c7840335a26dcf4e5e6da5090fdea01b47886b3b8bdbed4fc3fcf374f539832", "generation_seconds_batch": 24.868951832060702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47013112902641296, "target_z": 0.5898437588853255, "ce": 6.117925643920898, "genuineness": 4.030367851257324, "identity": 0.6801997423171997, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4c2d23f1804f9a5637cb911e7a81ccb24b0845cd1e7b107ee65e21ae9c77e035.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "4ccfeea76e6fdd6aead9d6dcd89f350b9a78a04959b7438e3b51fded8b5026ea", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6935777cd78ba9a98cce0039ff70aebb13791bb3d1b1116ec55453d7185b6778", "generation_seconds_batch": 24.320228012045845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010743096470832825, "target_z": -0.4726562368066379, "ce": 6.324435234069824, "genuineness": 4.319066047668457, "identity": 0.422707736492157, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4ccfeea76e6fdd6aead9d6dcd89f350b9a78a04959b7438e3b51fded8b5026ea.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "4d3582bcf3ead3734b97c28b0fc18bb39c545cb0f14630fad0c24d1e39940cfd", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1c7be0b9c68d7b8cb2a6dccd48c94c9d252df6a432ca747b4209f784f46568d8", "generation_seconds_batch": 17.440542632015422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0460550785064697, "target_z": 1.9218749623046796, "ce": 5.704906940460205, "genuineness": 3.6663577556610107, "identity": 0.5123673677444458, "hypothesis": "De deur 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_Sourness/4d3582bcf3ead3734b97c28b0fc18bb39c545cb0f14630fad0c24d1e39940cfd.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "4d80afb4069178749ac91ac9251d4705f742809910b37d5a82f206c09d3737f4", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "03c5dc0fba681194a1a68faa490e247ad4f3b5c75865b2aeea41b3d0f1adc1bd", "generation_seconds_batch": 25.814593910006806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07830014824867249, "target_z": -0.31640626480887585, "ce": 5.831989288330078, "genuineness": 4.400654315948486, "identity": 0.36136946082115173, "hypothesis": "J'ai trouvé la 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_Sourness/4d80afb4069178749ac91ac9251d4705f742809910b37d5a82f206c09d3737f4.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "4e25051b7e75293c53923277c6a38cfb1abc956e6bbcb856b4eafdddd75de812", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "71088cde96cf01eec79181a39cefba505df70edb9e1f12214b7c69ab00268f6b", "generation_seconds_batch": 17.71890732110478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39750728011131287, "target_z": 0.42187499676897255, "ce": 5.927301406860352, "genuineness": 3.936227321624756, "identity": 0.11424517631530762, "hypothesis": "Ik 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_Sourness/4e25051b7e75293c53923277c6a38cfb1abc956e6bbcb856b4eafdddd75de812.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "4e36960e6b97d078406e30e8944be8dc2af6b3a3cca93ea30c999f7dfc63fa92", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d49213051963ac1d39d1dbcd8be2af3a19150413eb9ba7103847778aade4c362", "generation_seconds_batch": 24.005008123000152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8568953275680542, "target_z": 1.4843750269252287, "ce": 5.990842819213867, "genuineness": 3.9550557136535645, "identity": 0.5881752967834473, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4e36960e6b97d078406e30e8944be8dc2af6b3a3cca93ea30c999f7dfc63fa92.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "4e4031d4002614983e35c2149d8d303a69d81440b9b1570891f3df7214a6c41d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "49135b6edd9415474e91a3a154d07cca69ab0016c59db50bd100a40a0720a7ef", "generation_seconds_batch": 22.504724208964035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1678132712841034, "target_z": -0.1093749838448627, "ce": 6.157639026641846, "genuineness": 4.143336772918701, "identity": 0.5694280862808228, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4e4031d4002614983e35c2149d8d303a69d81440b9b1570891f3df7214a6c41d.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "4e434651dd6ccc2988b336fc55deebb5d7090f96703673929725296b11d2836d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9e750c23e43d1a62677d44f8b9762c4fb607c518fd9eaf7cf2f9052baa6622dc", "generation_seconds_batch": 22.54659769393038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011212959885597229, "target_z": -0.5234375113085961, "ce": 6.070269584655762, "genuineness": 4.218649387359619, "identity": 0.5326005220413208, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4e434651dd6ccc2988b336fc55deebb5d7090f96703673929725296b11d2836d.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "4e5cb9855c3f956b37cea358008656f9bad3aa82f2c2e1e3853493b50189a237", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3ab16fe45d03ac679636f78dd21440d47bb02dea3e11edd9b0c338246161d267", "generation_seconds_batch": 23.344303463003598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1407904326915741, "target_z": -0.171875014001119, "ce": 6.141753673553467, "genuineness": 4.13078498840332, "identity": 0.7789158821105957, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4e5cb9855c3f956b37cea358008656f9bad3aa82f2c2e1e3853493b50189a237.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "4e8459f81b7a65e054908f1c2a130db5049642a476bea047c82402709e5162ea", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b1a9ce8011c997c4083cbd5c663cc82a072c5636c2c7b8c507cb0677bf3f5650", "generation_seconds_batch": 16.03644242999144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28266027569770813, "target_z": 0.15625000646205492, "ce": 6.0146708488464355, "genuineness": 4.143336772918701, "identity": 0.6275018453598022, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Het.", "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_Sourness/4e8459f81b7a65e054908f1c2a130db5049642a476bea047c82402709e5162ea.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "4f905697fb1fdbdbdfcf7b4225fe9d620bc631e32d5b0572078d93cfcfb7dc51", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8771a796fe5d9beb52fbec6dab50a526611c53cc1e9c80ebfbc3118ba2dbc16d", "generation_seconds_batch": 17.738243576022796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1744134426116943, "target_z": 2.2187498298325536, "ce": 5.839932441711426, "genuineness": 3.9048471450805664, "identity": -0.022048134356737137, "hypothesis": "De deur 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_Sourness/4f905697fb1fdbdbdfcf7b4225fe9d620bc631e32d5b0572078d93cfcfb7dc51.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "4facd7db460a3275eaa6be0b2488d13bd87b0f12e72bc0a1ec32e43f6ab2a3b1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d7ba0ec23fe7c25da1a8585cdffd8c0af0e514dc0ea3e3e0c7d022480b13118d", "generation_seconds_batch": 23.39210286992602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15092399716377258, "target_z": -0.14843750269252287, "ce": 6.109982967376709, "genuineness": 4.118232727050781, "identity": 0.6739736795425415, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/4facd7db460a3275eaa6be0b2488d13bd87b0f12e72bc0a1ec32e43f6ab2a3b1.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": "4fda5e543d7bea1c69181e32903f28857ac4c331a67ac8e5f2a3abcba00d62df", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59a97279fb69f4c8100819d21723661b5b2c08adb8e187a06d9bb127e927b493", "generation_seconds_batch": 27.20446896390058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18132467567920685, "target_z": -0.07812500323102746, "ce": 5.911416053771973, "genuineness": 4.111956596374512, "identity": 0.7169152498245239, "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_Sourness/4fda5e543d7bea1c69181e32903f28857ac4c331a67ac8e5f2a3abcba00d62df.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "500ac0ef3ff5236cf4637607c151fd66295b08af3bf060abcd75c4b89b810229", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "145867c3c45542fe1fd7899eb86d97a20e635db3d333213a9f4fde2f314e0e75", "generation_seconds_batch": 21.778999811969697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1202123165130615, "target_z": 4.406249782444151, "ce": 5.696964263916016, "genuineness": 3.5973212718963623, "identity": 0.5796856880187988, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/500ac0ef3ff5236cf4637607c151fd66295b08af3bf060abcd75c4b89b810229.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "50552382bf479419cff77484a321a46425ec4978f35fd3bc989f0bddf06d7781", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "083694fda4fa7f53f98ce50d74b6e31ed04be74ccd266bd1641f92ca3265e11f", "generation_seconds_batch": 26.6967051459942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19145824015140533, "target_z": -0.05468749192243135, "ce": 5.982900142669678, "genuineness": 4.118232727050781, "identity": 0.6389568448066711, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/50552382bf479419cff77484a321a46425ec4978f35fd3bc989f0bddf06d7781.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": "509737d7da35692efabe6408bdfb69b32ae8dc951b0defb02d4d096cfa8e0308", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00594764f5382f409bfdede44664d3cc6740593b2f5735abcc72e1c37708eaa2", "generation_seconds_batch": 14.483398671029136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09012264013290405, "target_z": -0.2890625016155137, "ce": 6.078212261199951, "genuineness": 4.337893962860107, "identity": 0.6694849729537964, "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_Sourness/509737d7da35692efabe6408bdfb69b32ae8dc951b0defb02d4d096cfa8e0308.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "51dda171113e76bfbb43a5b129aa73dd36d72bf537d37efe2126aa08a06127a1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "be3e601e14f09b01291b78d1f37853a07e17cd2f83ce093b529314d7dd607241", "generation_seconds_batch": 23.62936045206152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4515529274940491, "target_z": 0.5468749881528994, "ce": 6.054384231567383, "genuineness": 4.061748504638672, "identity": 0.6454630494117737, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/51dda171113e76bfbb43a5b129aa73dd36d72bf537d37efe2126aa08a06127a1.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "51ff97cb4d8c0c1f5d82f56b0675b0fb3960f3a5485340f0b76bf4d13df30dac", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8c8b26c785843a212cfb5337be4367daacc238b2f60b0f49253ac61383fa59b4", "generation_seconds_batch": 23.10034234903287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0561885833740234, "target_z": 1.9453123357561042, "ce": 5.295859336853027, "genuineness": 3.6977379322052, "identity": 0.17642652988433838, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/51ff97cb4d8c0c1f5d82f56b0675b0fb3960f3a5485340f0b76bf4d13df30dac.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "5293a5acc9a024a6884eac7ed241f047742691fbeff50c946d8f473f6a4b8012", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a6a43d403151dc7c45bc77cbb51316c3f87cbdf6aeab77f6c9e50a2b67638b1", "generation_seconds_batch": 17.315387034090236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20159178972244263, "target_z": -0.03125001507812814, "ce": 5.756534099578857, "genuineness": 3.8420867919921875, "identity": 0.7187236547470093, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5293a5acc9a024a6884eac7ed241f047742691fbeff50c946d8f473f6a4b8012.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "539a6c5a5951af156ba1601039f105052c01e018ab91cbae214f900496b03538", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ce5a319d04950de8513dbda39b5d09357b15023ad29fe1dc43321f2cd502da70", "generation_seconds_batch": 23.851929930970073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07830014824867249, "target_z": -0.31640626480887585, "ce": 6.133810997009277, "genuineness": 4.482243061065674, "identity": 0.5694595575332642, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/539a6c5a5951af156ba1601039f105052c01e018ab91cbae214f900496b03538.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "53a10fdb912b5848bd0f87d12524d61edd0afe20d7ad99f5edecb1051949d317", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "02a8e6c2d52c3d65de0c185f9307b6f6043baafab380103e15ae413912701cf3", "generation_seconds_batch": 23.908777602016926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.1894097328186035, "genuineness": 3.9927117824554443, "identity": 0.6191772222518921, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/53a10fdb912b5848bd0f87d12524d61edd0afe20d7ad99f5edecb1051949d317.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "53ae9ba34546cd177d7c6e0dc166d776a52e4f8ccd7ba4e85ed3a7944cef6229", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f80a41d8dfbd5440d506a44092bb64713cc4c90085668bb7b2803741b1b5a37a", "generation_seconds_batch": 23.095848183962516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16950219869613647, "target_z": -0.10546873196009669, "ce": 6.046441555023193, "genuineness": 4.2374773025512695, "identity": 0.2699905037879944, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/53ae9ba34546cd177d7c6e0dc166d776a52e4f8ccd7ba4e85ed3a7944cef6229.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": "53af9e0d8775c9b0cacaf6561f313ceda98fb8415fbcab44b1a32061f74a80d2", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I wrote the number on the envelope.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce0345cb8c36749275584638eef4fffc8b97af468e925378dede9ef21ff9dbec", "generation_seconds_batch": 25.156896093976684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09350049495697021, "target_z": -0.2812499978459817, "ce": 6.292664527893066, "genuineness": 4.055472373962402, "identity": 0.5824622511863708, "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_Sourness/53af9e0d8775c9b0cacaf6561f313ceda98fb8415fbcab44b1a32061f74a80d2.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "53c602b646b38533fc398f5c713c7901e84c9cfb02bf0a7736a8f87707d713bb", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de20de2c35bcbade65dbccdca89f65825fa59ff5c9cfca1e1797b2dec5e2113e", "generation_seconds_batch": 22.408450578106567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07830014824867249, "target_z": -0.31640626480887585, "ce": 6.09409761428833, "genuineness": 3.747946262359619, "identity": 0.049554839730262756, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/53c602b646b38533fc398f5c713c7901e84c9cfb02bf0a7736a8f87707d713bb.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": "54575f450238f8e4e318f279db56676aacb7846e56d4c648bce98d89d56aa0ac", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c65314384c4cad1393c95086c80ff21866808cbc8c5fc59f45e1852d63db2034", "generation_seconds_batch": 14.472811475978233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1323457956314087, "target_z": -0.19140627342494906, "ce": 6.038498878479004, "genuineness": 4.143336772918701, "identity": 0.5556762218475342, "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_Sourness/54575f450238f8e4e318f279db56676aacb7846e56d4c648bce98d89d56aa0ac.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "41c3a17419901afa9f64c7398742d2c23d60d06f7426dd54488e49e16a82d5fb", "generation_seconds_batch": 17.623068492044695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0267878919839859, "target_z": -0.4355468783656536, "ce": 6.332377910614014, "genuineness": 3.6789097785949707, "identity": 0.5356518030166626, "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_Sourness/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "54f8f744c390e88bc7dd2a8a8fcc9c6a28e6fd2ca4214036063a5ccccd648f59", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a1b1fb634907dc493eb0cb3d417006eb49286368b4b002300f14fbb751ee196", "generation_seconds_batch": 21.860219744965434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7554042339324951, "target_z": 3.5624999267633775, "ce": 5.974957466125488, "genuineness": 4.093128204345703, "identity": 0.7337366342544556, "hypothesis": "J'ai trouvé la 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_Sourness/54f8f744c390e88bc7dd2a8a8fcc9c6a28e6fd2ca4214036063a5ccccd648f59.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": "555f41ab6cf153635461e0582b04449ac3d8b07a61d12fc5a1f483d01385489b", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "84fc6e5ccf6391764f448f64b0640ef4689b787ea036456deddb44442b45481e", "generation_seconds_batch": 24.048293755971827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.052810788154602, "target_z": 1.9374999698437436, "ce": 6.133810997009277, "genuineness": 3.7416701316833496, "identity": 0.30217382311820984, "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_Sourness/555f41ab6cf153635461e0582b04449ac3d8b07a61d12fc5a1f483d01385489b.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "55dc78300f5964de5da407f89eb3255b690be2a931bdb83c0a0ebba3adbae3dc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7544c5d7709b1a3d4b0ccfdee7d246b723733ff14384245519b4035cf93b8cb4", "generation_seconds_batch": 19.036507615004666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029321283102035522, "target_z": -0.4296875005385046, "ce": 6.078212261199951, "genuineness": 4.193545341491699, "identity": 0.4432395398616791, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/55dc78300f5964de5da407f89eb3255b690be2a931bdb83c0a0ebba3adbae3dc.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": "5678bf5908c935b49db633eae632e656d0363da0ea92ad920873c5de5800a5ff", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4da5136165602c4bf98bbb31ee5bbfbeaef1199cb0ad4d4a12d1d4426e6b091", "generation_seconds_batch": 18.753390555037186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11967885494232178, "target_z": -0.2207031280964013, "ce": 6.173524379730225, "genuineness": 4.582659721374512, "identity": 0.6975414752960205, "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_Sourness/5678bf5908c935b49db633eae632e656d0363da0ea92ad920873c5de5800a5ff.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": "575e1acea636e6ae748ac571501c6749a78e86325b05d3e7bd70588847986012", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2d897584dd6a89a2efd10d61d96b935226245df24f6120c77607734dd8af019", "generation_seconds_batch": 18.382263578940183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2987050712108612, "target_z": 0.1933593649030392, "ce": 6.229123115539551, "genuineness": 4.281409740447998, "identity": 0.4594205915927887, "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_Sourness/575e1acea636e6ae748ac571501c6749a78e86325b05d3e7bd70588847986012.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "576dde201b622f16660e09371791a7e751d45723b168ddf7f0dd4d7030eb1356", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a97d3d0aae26978c5ead55640cf7f7273211f8f0c2156f3e812f33bb9386878c", "generation_seconds_batch": 16.990537362988107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18808038532733917, "target_z": -0.06249999569196339, "ce": 5.919358730316162, "genuineness": 3.600459337234497, "identity": 0.48910850286483765, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/576dde201b622f16660e09371791a7e751d45723b168ddf7f0dd4d7030eb1356.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "57797ed0d54858bd7c6c9ee0ea5f726c76d87100f1c91be82c9a14c5b550dce7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d874a89e95cf2ebe1094bdf3424f1cf0225dd755b98f33f666e9c804d3223871", "generation_seconds_batch": 23.86193348793313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.691380500793457, "target_z": 1.1015624800753308, "ce": 6.165581703186035, "genuineness": 4.105680465698242, "identity": 0.6748557686805725, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/57797ed0d54858bd7c6c9ee0ea5f726c76d87100f1c91be82c9a14c5b550dce7.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "579dbd7acd97928bea6ef5b8d23d9c26cbb5ba6b61803424f992ae747f1d27ec", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "22731cd9c82a254cfb37e125c9330cbebb7d1f5f20f66eaa8e3ea6df08603b9c", "generation_seconds_batch": 25.76587558502797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04621054232120514, "target_z": -0.3906250161551373, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.45319023728370667, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/579dbd7acd97928bea6ef5b8d23d9c26cbb5ba6b61803424f992ae747f1d27ec.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "57ae78b3c3b4490702d5561a8972acea2212807cfc795df72d50c35a178e0980", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "41d4efac739689d8549c4e3c74e4f051f170d6632ca4f178dacd24942412e59f", "generation_seconds_batch": 26.6967051459942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6508462429046631, "target_z": 1.0078124348409463, "ce": 6.133810997009277, "genuineness": 4.086852550506592, "identity": 0.7016581296920776, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/57ae78b3c3b4490702d5561a8972acea2212807cfc795df72d50c35a178e0980.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "58005e705e276a0b433fabc667296460c5c77e7f2ee79e8aa378e867e513b19d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a138c24d300e0b728d1cc2a766e9c59a6ecbeb2aa591c18ef58cb46c5bdc0b9e", "generation_seconds_batch": 32.58281185606029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007835105061531067, "target_z": -0.515625007539064, "ce": 6.23706579208374, "genuineness": 4.444586753845215, "identity": 0.3548204302787781, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/58005e705e276a0b433fabc667296460c5c77e7f2ee79e8aa378e867e513b19d.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": "58165faafc3dd5e3f7c1bfce166f3e99dae1efd4b9379695f62e292de223e298", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e980daf65ce9ac45baa035c98bd93a80772d1e05379ab393f6d2af7da8303b0a", "generation_seconds_batch": 16.21318983391393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0951894223690033, "target_z": -0.2773437459612157, "ce": 6.149696350097656, "genuineness": 4.13078498840332, "identity": 0.6027950048446655, "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_Sourness/58165faafc3dd5e3f7c1bfce166f3e99dae1efd4b9379695f62e292de223e298.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "584cc8b6b7e3059b1ed5f61af3be3b846f3a3647993dddba16bdbd7b7ae13e2e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "78916f645723842eb007acb8ddd4d7592e532bc7d9a17442a85c8afc7a64f3f7", "generation_seconds_batch": 23.53093796595931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04114377498626709, "target_z": -0.40234373734514245, "ce": 6.0305562019348145, "genuineness": 4.570107460021973, "identity": 0.5928331613540649, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/584cc8b6b7e3059b1ed5f61af3be3b846f3a3647993dddba16bdbd7b7ae13e2e.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "588b3dd7e6e35733b312ad48c0c4d17273d5c8630e5aefdbf053dad058a16f75", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "64746338538bd1af6a41ad55bc5e6bc82dbb521aa3f65b8200635f1d83e03d17", "generation_seconds_batch": 22.53122924407944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7758268117904663, "target_z": 1.29687493645646, "ce": 5.696964263916016, "genuineness": 4.080576419830322, "identity": 0.7281901240348816, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/588b3dd7e6e35733b312ad48c0c4d17273d5c8630e5aefdbf053dad058a16f75.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "58ec6f62138407cf6fffa036d5012f7303f39f7bd57830be3682cb7bf5780fe9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "988289be556b381168c94120535eeef3cfb15213c799b9abab45812d3514d5de", "generation_seconds_batch": 25.40885729098227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014120951294898987, "target_z": -0.46484373303710586, "ce": 6.356205940246582, "genuineness": 4.406930446624756, "identity": 0.5291129350662231, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/58ec6f62138407cf6fffa036d5012f7303f39f7bd57830be3682cb7bf5780fe9.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "58fea714827524032fcc68227a630f3dcdb4a377765365a492f1bdb9afec926d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "94a1397c87a027771bdb446126bd6eb4ad3af28c43ec42ff5787eaf4aaf4bc37", "generation_seconds_batch": 23.643025108030997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08336693048477173, "target_z": -0.3046875091545778, "ce": 6.1020402908325195, "genuineness": 3.8169827461242676, "identity": 0.24686911702156067, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/58fea714827524032fcc68227a630f3dcdb4a377765365a492f1bdb9afec926d.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "5a8b2dba173635dfa2e71e27b94057744352b9d9eab06b8fa722c11d1ce9ae81", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a252772fe1617ccb8421ff2b4ff5e3bba80dcaa6ca98241e4160657e9311e9b7", "generation_seconds_batch": 24.62609562498983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05972196161746979, "target_z": -0.35937500107700915, "ce": 6.141753673553467, "genuineness": 3.8671910762786865, "identity": 0.49545037746429443, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5a8b2dba173635dfa2e71e27b94057744352b9d9eab06b8fa722c11d1ce9ae81.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "5a981388d3fbe10ea98acf0cc73d35e172d867e4d052ae1740d33f6c5ecfe2cc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a7b36a2c3e66cbd8195f0fd2f2c2b048122af47f1fb30861ec2e0131e56baa77", "generation_seconds_batch": 21.855871148989536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11967885494232178, "target_z": -0.2207031280964013, "ce": 6.165581703186035, "genuineness": 4.6203155517578125, "identity": 0.6706220507621765, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5a981388d3fbe10ea98acf0cc73d35e172d867e4d052ae1740d33f6c5ecfe2cc.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": "5ae6e2013211c9298eff88efaab5aab7301cbe4144a2fa555bd9a6191245f60a", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I wrote the number on the envelope.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dbd5a59f3d1d7a50ed515967c372ecec2873840c52d51194c43299bd7edcbb21", "generation_seconds_batch": 22.650942674954422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08843371272087097, "target_z": -0.29296875350027973, "ce": 6.443574905395508, "genuineness": 3.8671910762786865, "identity": 0.3634433150291443, "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_Sourness/5ae6e2013211c9298eff88efaab5aab7301cbe4144a2fa555bd9a6191245f60a.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "5b4ad4f64b2e744125e313d5815faa38977cfcde846a74393e1b6dd56d5bce17", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "494f031f0aa5a470c7fd29bd6f47072a74d0c0fdd200dc34f7a652f3601e0a2d", "generation_seconds_batch": 23.776870236033574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12390117347240448, "target_z": -0.21093749838448628, "ce": 6.062326908111572, "genuineness": 4.086852550506592, "identity": 0.728340744972229, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5b4ad4f64b2e744125e313d5815faa38977cfcde846a74393e1b6dd56d5bce17.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "5ba899c3841bd5fe8f4aa88e557f621c83d8e8caf7c152303b989ffd0cce52b9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0e1eae448a6a130501431c7df1bd4ebeeadf47dd9b3e116ad6a15b3ef5c9fcd7", "generation_seconds_batch": 21.511059255921282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3071497082710266, "target_z": 0.21289062432686928, "ce": 5.974957466125488, "genuineness": 3.565941095352173, "identity": 0.42678922414779663, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5ba899c3841bd5fe8f4aa88e557f621c83d8e8caf7c152303b989ffd0cce52b9.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "5c2e5efc3d19156a560f5a60b4794a9f3300d6a6328b521a04deea8d01880d43", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7b5fac4c023078c6ab9b972c5e9b7143e4d29f7314c6a0fc9660138ef96b5688", "generation_seconds_batch": 26.577459005988203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02341003715991974, "target_z": -0.44335938213518566, "ce": 6.022613525390625, "genuineness": 3.747946262359619, "identity": 0.26753371953964233, "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_Sourness/5c2e5efc3d19156a560f5a60b4794a9f3300d6a6328b521a04deea8d01880d43.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "5cb4cace02e2fe53c762fc8dd1f30e90ad4618d05b247ab494a239500432c811", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fbb15d2c975869a2f3cb53e625cf93a665c146d8cd423ecb35294e33a166a3dd", "generation_seconds_batch": 24.066893849987537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031854674220085144, "target_z": -0.42382812271135556, "ce": 6.181467056274414, "genuineness": 4.406930446624756, "identity": 0.649950385093689, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5cb4cace02e2fe53c762fc8dd1f30e90ad4618d05b247ab494a239500432c811.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "5cce38c6d25f24fe0ccf2a31f5a063d596fc9208f171478c860a227b6abdc56f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ba841484070d94adbdb46e19bb671dacd98f96d43ecc3963d9b37bca24827d23", "generation_seconds_batch": 17.99024648591876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4599975645542145, "target_z": 0.5664062475767294, "ce": 6.038498878479004, "genuineness": 4.017816066741943, "identity": 0.43126145005226135, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5cce38c6d25f24fe0ccf2a31f5a063d596fc9208f171478c860a227b6abdc56f.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "5dbea62ad06f9852c4cf1334a611c5d7d7fec11b7ffe010df7b6da2024cd40da", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7759ab9ba23049aca4e4a7564abf1c415488698ec30d7460f02fdcbd5a55aaa5", "generation_seconds_batch": 24.424193218001164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0010793954133987427, "target_z": -0.5, "ce": 6.38003396987915, "genuineness": 4.444586753845215, "identity": 0.30422455072402954, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5dbea62ad06f9852c4cf1334a611c5d7d7fec11b7ffe010df7b6da2024cd40da.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "69fe2781db4b4bc6311090191548598daeb32444745cfc67ae939f39c59b8ddf", "generation_seconds_batch": 17.512150016031228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07323338091373444, "target_z": -0.328124985998881, "ce": 6.125868320465088, "genuineness": 4.168440818786621, "identity": 0.7548813819885254, "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_Sourness/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "5ef774255d2681eab058f29a31b7ad5dc89634b3d499d50c454aede818e5a958", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2e57d5d0c3bcccd467ed5db6cebb5dc625ce7acb5512f3680533024eeb00625e", "generation_seconds_batch": 24.036074834060855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13741257786750793, "target_z": -0.17968751777065103, "ce": 6.125868320465088, "genuineness": 4.406930446624756, "identity": 0.5986988544464111, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5ef774255d2681eab058f29a31b7ad5dc89634b3d499d50c454aede818e5a958.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": "5f09734bba182d094eaf02f7262e7142181c48db1c2b06ebfb123ee8e3aa1185", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The keys are on the kitchen table.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8fac6f3d65b2ec8e95293271caf187271bfa4a1f156e3f575c08db4a54fc06cb", "generation_seconds_batch": 25.321224396000616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08167800307273865, "target_z": -0.30859376103934383, "ce": 6.09409761428833, "genuineness": 4.093128204345703, "identity": 0.5014777183532715, "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_Sourness/5f09734bba182d094eaf02f7262e7142181c48db1c2b06ebfb123ee8e3aa1185.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "5f129758c01315412859bb3ea4f0916f574ac0abd8a2fce43894f928a355d089", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a395a5c82799b30aa5550b81e8108e0292698a7693eaa54583614a8041862f8a", "generation_seconds_batch": 22.975997025030665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09856727719306946, "target_z": -0.2695312421916836, "ce": 5.732706069946289, "genuineness": 3.9550557136535645, "identity": 0.036157652735710144, "hypothesis": "Ich hab die kleine Schachtel gefunden! Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5f129758c01315412859bb3ea4f0916f574ac0abd8a2fce43894f928a355d089.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": "5f9520782817613a8ca98a28257af9213df34d803f45b8bb1ec5dc52eb9c3004", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I wrote the number on the envelope.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7e3f9d855519a46ccd3764fa763a2e21fca6aaaf42668fc19e82641bed12378", "generation_seconds_batch": 25.156896093976684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15599077939987183, "target_z": -0.13671874703822484, "ce": 6.268836498260498, "genuineness": 3.9550557136535645, "identity": 0.4774869978427887, "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_Sourness/5f9520782817613a8ca98a28257af9213df34d803f45b8bb1ec5dc52eb9c3004.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "5fac980e779723ab26159f642bc8e5f1caf4496aa04b137042421805b62cae08", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8392bf160dc63a7bba99bde693cecde70fd018a61769e50e5bbd2ed640cdce4f", "generation_seconds_batch": 17.213262684061192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05296625196933746, "target_z": -0.37500000861607324, "ce": 6.0305562019348145, "genuineness": 4.005263805389404, "identity": 0.3820759654045105, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5fac980e779723ab26159f642bc8e5f1caf4496aa04b137042421805b62cae08.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "5fae2b2a44ebeb908bb75ad5b0ca821299ca680f63c8cbe3d571202569c7da8b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c5a52162914ceab7add9ec97042d140888a7aa8cf52199bcbe57afa1b5fee444", "generation_seconds_batch": 24.8731915949611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01965758204460144, "target_z": -0.5429687362681334, "ce": 6.070269584655762, "genuineness": 4.507347106933594, "identity": 0.6213760375976562, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5fae2b2a44ebeb908bb75ad5b0ca821299ca680f63c8cbe3d571202569c7da8b.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "5fb37b7d195af6fe3d01115c336a38900f4499e2f62fd08be2e845e12f2d9fbf", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "80a34146a55f62460e8c7df9c4e24c6dad7362f6acf2cf4d7f3ad9e77008686d", "generation_seconds_batch": 25.11398461693898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08336693048477173, "target_z": -0.3046875091545778, "ce": 6.133810997009277, "genuineness": 4.21237325668335, "identity": 0.49329307675361633, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/5fb37b7d195af6fe3d01115c336a38900f4499e2f62fd08be2e845e12f2d9fbf.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "60440b83c7a8df60d71b0b34507077e48c7f51c900c3eb50decdd2083f7dc0db", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bd91c2d50eb6e6021467f0b2b0eb701f13bcdb9538919d05184aaa0ba73d1c58", "generation_seconds_batch": 23.748547647963278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12727902829647064, "target_z": -0.20312499461495423, "ce": 6.006728172302246, "genuineness": 4.293961524963379, "identity": 0.8014369010925293, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/60440b83c7a8df60d71b0b34507077e48c7f51c900c3eb50decdd2083f7dc0db.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "6139348f57032feb0f4d608155ce8320f25636394e860f743412e41f4cba7e24", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5cb4afcbd41d3f91ff07ef7941418abf000d7efd5d662f5fe5efa802c6ec14ef", "generation_seconds_batch": 27.29190336097963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10025619715452194, "target_z": -0.2656250075390641, "ce": 5.80021858215332, "genuineness": 4.375550270080566, "identity": 0.6031368970870972, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6139348f57032feb0f4d608155ce8320f25636394e860f743412e41f4cba7e24.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "616dcdb7a40cb37de2a6f8a732d78c48017e53742fe1036ba6460b8a313fa50d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3e01a30916ec7678dafa4574912bcfd309dbdf9e0922074dce39207e712159b1", "generation_seconds_batch": 25.541611508000642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014590814709663391, "target_z": -0.5312500150781282, "ce": 6.205295085906982, "genuineness": 4.042920112609863, "identity": 0.4766901135444641, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/616dcdb7a40cb37de2a6f8a732d78c48017e53742fe1036ba6460b8a313fa50d.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "61aa97c8c0a89815339fc7dcd2c79dca132f1d28fe50e1f51f304b61b228d674", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "30840743a4d209a4449cda7d9d273d8737eb9e7da561c70abe712252baf1a4ee", "generation_seconds_batch": 25.610020303050987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0909671038389206, "target_z": -0.2871093756731307, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.6823421716690063, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/61aa97c8c0a89815339fc7dcd2c79dca132f1d28fe50e1f51f304b61b228d674.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "61d3d704ac7e0f122c4239cf27d656e912dd7ad5046c4dd7d3d9472dd9e19a5d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "51816b8e3ddcec3ac46ec69b1bf5a5b9892f8403c2508b1699024f153f125ca3", "generation_seconds_batch": 23.782783022033982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08758924901485443, "target_z": -0.29492187944266274, "ce": 6.086154937744141, "genuineness": 3.760498285293579, "identity": 0.36577099561691284, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/61d3d704ac7e0f122c4239cf27d656e912dd7ad5046c4dd7d3d9472dd9e19a5d.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "61d7bd12ff8b5e48bb486149a2124346dcdc2c951edba6a171677ffdb493c550", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7800e4e724d022ffe81cae220153fcdf67a95f84f81f9975f6376dedae87ee01", "generation_seconds_batch": 20.632799664977938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20159178972244263, "target_z": -0.03125001507812814, "ce": 6.09409761428833, "genuineness": 4.243753433227539, "identity": 0.3576255142688751, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/61d7bd12ff8b5e48bb486149a2124346dcdc2c951edba6a171677ffdb493c550.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "62352fbf111894eb0860cbb13eb4bcc51ad925c4d99c8fd44f752718c5b70dff", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "330720166b51b1c98d2a8e7293d72f6bc5bc5833eb62dd1028276833644415a1", "generation_seconds_batch": 24.36039363697637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021721109747886658, "target_z": -0.4472656340199517, "ce": 6.205295085906982, "genuineness": 4.519899368286133, "identity": 0.6360737085342407, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/62352fbf111894eb0860cbb13eb4bcc51ad925c4d99c8fd44f752718c5b70dff.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "623b6b975b399e216e08ccf2f7a943ee48a89c9baa958e38366df00cf8e73637", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "571ff2d877f812a431a9210a3c7d935d6f047e6241d5ce96ea232f0e4cdb353f", "generation_seconds_batch": 16.238349042949267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10194512456655502, "target_z": -0.26171875565429803, "ce": 6.260893821716309, "genuineness": 4.030367851257324, "identity": 0.2684088349342346, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/623b6b975b399e216e08ccf2f7a943ee48a89c9baa958e38366df00cf8e73637.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "6292ef240d548ab0ae1208c6dbbb98c56f3dd002869735f174da5d864f550a28", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "475e971d24abd6d02f8b4fb7a62ec436c669916bd63bdf4198803257c86baf71", "generation_seconds_batch": 18.20911829790566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41777437925338745, "target_z": 0.46874995045757895, "ce": 5.411027908325195, "genuineness": 3.4498343467712402, "identity": 0.3414016366004944, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6292ef240d548ab0ae1208c6dbbb98c56f3dd002869735f174da5d864f550a28.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "62a692d57ca12995360495bb02ccd98494fb137fa44b7f1fd944ad8923a90d4c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a844ed732f04ed3641af1ed6d229be9c247dd6b320e1d16a6d7b9a65136701fa", "generation_seconds_batch": 25.483128646039404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06394428014755249, "target_z": -0.3496093713650941, "ce": 6.09409761428833, "genuineness": 4.20609712600708, "identity": 0.49818938970565796, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/62a692d57ca12995360495bb02ccd98494fb137fa44b7f1fd944ad8923a90d4c.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "62e6b798be605ffa73e3e9bf5abfc758ee07bc6f0c7966fe2ad5aedddd21cd7f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c8a068e11173e8b78f9303d4659499efbec9f0dcfb9e043d10ac89ae5eb01a4e", "generation_seconds_batch": 26.27216082101222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010743096470832825, "target_z": -0.4726562368066379, "ce": 6.284721851348877, "genuineness": 4.319066047668457, "identity": 0.4144454598426819, "hypothesis": "I found the little box. It was beside the old window. We can look inside together?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/62e6b798be605ffa73e3e9bf5abfc758ee07bc6f0c7966fe2ad5aedddd21cd7f.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": "630a07c0cc4c9052e0aecce5059791ab5553bbab1f13e3754a2b217448ab7044", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3408165730899f07fad6e8fd4348b41b8ca775ede591535971c78677b9ebe9ae", "generation_seconds_batch": 18.56141291500535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07998907566070557, "target_z": -0.31250001292410984, "ce": 6.165581703186035, "genuineness": 4.545003414154053, "identity": 0.758628249168396, "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_Sourness/630a07c0cc4c9052e0aecce5059791ab5553bbab1f13e3754a2b217448ab7044.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "6328c29269b370c04d2b6aba2784f1f12fba91422a3506ce9b3246fff4800ca0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7aeaf7a623c997af9a2e4a6eec3f4d283d2bbcbbd7403227d959286d6cdc69e6", "generation_seconds_batch": 23.99027109402232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08843371272087097, "target_z": -0.29296875350027973, "ce": 6.022613525390625, "genuineness": 4.256305694580078, "identity": 0.4453076124191284, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6328c29269b370c04d2b6aba2784f1f12fba91422a3506ce9b3246fff4800ca0.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "634579e2959e3bd74076ebb7cc7d98cba65d156ac544bf3dceba2314d87d80b2", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c2f8b6fed5ee7c5a20864bae2dab748368ccbfc182d6f20c9d05586fc031b7dd", "generation_seconds_batch": 23.35217729001306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27083778381347656, "target_z": 0.1289062432686928, "ce": 5.8875885009765625, "genuineness": 3.848362922668457, "identity": 0.6520764231681824, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/634579e2959e3bd74076ebb7cc7d98cba65d156ac544bf3dceba2314d87d80b2.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "63985356991a7f89c9a168a75e46605c8fa362d85ba95c52bdc4ec97155f3622", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b2475b8f98b1c01ac1110a81d3f7644d77ac432be3fbbc8f06bf1ed650bb19d3", "generation_seconds_batch": 27.26717461401131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04789946973323822, "target_z": -0.3867187642703713, "ce": 6.1020402908325195, "genuineness": 4.344170093536377, "identity": 0.5315298438072205, "hypothesis": "J'ai trouvé la 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_Sourness/63985356991a7f89c9a168a75e46605c8fa362d85ba95c52bdc4ec97155f3622.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "642059c40a904ba089ef429b68ba5bfdf27fa2f5c8a61aad8bbf28eeea153c8f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b589bdb1895cc2456486527b6028cfadbd50e5cab71bd3e6b991c930be679fd3", "generation_seconds_batch": 22.779177734977566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4000406861305237, "target_z": 0.42773440906041443, "ce": 6.078212261199951, "genuineness": 4.055472373962402, "identity": 0.7083209156990051, "hypothesis": "Ik 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_Sourness/642059c40a904ba089ef429b68ba5bfdf27fa2f5c8a61aad8bbf28eeea153c8f.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "645e8538327ef81251c47cb4607e0a12abb7df42d83ce5ebbb0f2539d96036aa", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c41c42775920be20f643d06385498dcaa66f3f1df022a488a7284fc6ad726eab", "generation_seconds_batch": 26.70786864904221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0056763142347335815, "target_z": -0.4843749924609359, "ce": 6.356205940246582, "genuineness": 4.607763767242432, "identity": 0.7189596891403198, "hypothesis": "J'ai trouvé la 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_Sourness/645e8538327ef81251c47cb4607e0a12abb7df42d83ce5ebbb0f2539d96036aa.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "64a83be21b02549e01258ccb5d60660a2855b542ef24d1594d9553254371d83b", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "83c6789a48d678ad11215cf6b9cd78b92444fdda5c7cf143c93b641b4365b988", "generation_seconds_batch": 15.337394253001548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011212959885597229, "target_z": -0.5234375113085961, "ce": 6.213237762451172, "genuineness": 4.632867813110352, "identity": 0.7533599138259888, "hypothesis": "J'ai trouvé la 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_Sourness/64a83be21b02549e01258ccb5d60660a2855b542ef24d1594d9553254371d83b.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "64cd2c6a510f066df08e8fb11772366b004be082c2b608f75c0381fb26f6598a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e39ba334a6c50113bf4fd4906b2fc66e86e7ea315673d6f1d070bbbb74b53f33", "generation_seconds_batch": 21.137825682992116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.028102219104766846, "target_z": -0.5624999956919634, "ce": 6.109982967376709, "genuineness": 4.105680465698242, "identity": 0.46418702602386475, "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_Sourness/64cd2c6a510f066df08e8fb11772366b004be082c2b608f75c0381fb26f6598a.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "65909df4c7ad990d7f8eed0fe2a2a0124165e2a2cc6ebd407c4334f02d07626d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e1cbb9333bbe0daf5a0904783dfe8599ebf5ba67800eb368866376bcbb78bd98", "generation_seconds_batch": 24.87057866191026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09181156754493713, "target_z": -0.2851562497307477, "ce": 5.700935363769531, "genuineness": 4.18099308013916, "identity": 0.6815406084060669, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/65909df4c7ad990d7f8eed0fe2a2a0124165e2a2cc6ebd407c4334f02d07626d.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "65c4f93b6e02cb40178ecc2ccf1fe5a3f2cfe1078bcee96ebbf4f29738a21f30", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2a0e1ca6dad55c4c224713274f3c10be5062b75ad98d89a01eda1c570ab45c08", "generation_seconds_batch": 18.254128454020247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009524032473564148, "target_z": -0.51953125942383, "ce": 6.205295085906982, "genuineness": 4.319066047668457, "identity": 0.5690471529960632, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/65c4f93b6e02cb40178ecc2ccf1fe5a3f2cfe1078bcee96ebbf4f29738a21f30.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "66206ceeb22d3a363f6df66a9b4e12ff93d6c0dd9764a74e9954e68953224dcb", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1087677b96878c59349e351cadd38da2e556c469f92866ad16438fb03f3b3fd8", "generation_seconds_batch": 23.9541149380384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.38797664642334, "genuineness": 4.268857479095459, "identity": 0.4445406198501587, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/66206ceeb22d3a363f6df66a9b4e12ff93d6c0dd9764a74e9954e68953224dcb.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": "66255ec067d2e21f4231684bfe7a7804a34915591573b916b41382a3fb6a8508", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4fe73cda20363d9f82652cc2aef0474118bc00eade6ec31255006f0f1e29ce20", "generation_seconds_batch": 14.407023231964558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4768868386745453, "target_z": 0.6054687664243896, "ce": 6.141753673553467, "genuineness": 4.15588903427124, "identity": 0.4449251890182495, "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_Sourness/66255ec067d2e21f4231684bfe7a7804a34915591573b916b41382a3fb6a8508.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "663957e14d92d84f6ec2943f0116b9938184440eb1cc35ba2d2bf93e39c093c8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "721259df14cc3bcd0e5eb438575851213378cbe0896f69bda508d821991cb42f", "generation_seconds_batch": 23.414696492953226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1433238387107849, "target_z": -0.16601560170967708, "ce": 6.260893821716309, "genuineness": 4.532451152801514, "identity": 0.6111594438552856, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/663957e14d92d84f6ec2943f0116b9938184440eb1cc35ba2d2bf93e39c093c8.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "665098e5a9e8b2d0285d1783f35ed44ab0705615b9385b90840d28ce0da49271", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "55fefd352d1f98875ac5f26bae6affad561b856ad64d1a6538b1b6ac6f1bfe02", "generation_seconds_batch": 26.791540961014107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001453995704650879, "target_z": -0.494140622172851, "ce": 6.046441555023193, "genuineness": 4.256305694580078, "identity": 0.7668787240982056, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/665098e5a9e8b2d0285d1783f35ed44ab0705615b9385b90840d28ce0da49271.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "667848b13179bb2f8ba49fc20d8b389a23b05d572f08ea84f8916a07f583016b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ff138ab40b9ce26db81799ed8c9cb42b84544ddbc42137617aa23729f674188f", "generation_seconds_batch": 23.095848183962516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13572365045547485, "target_z": -0.18359376965541704, "ce": 5.974957466125488, "genuineness": 4.457139015197754, "identity": 0.612699031829834, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/667848b13179bb2f8ba49fc20d8b389a23b05d572f08ea84f8916a07f583016b.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "66e110e0638616fb58e8e6249e287b0ffc24fd61998d656453cd41a4d6e7b442", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "820b432eee19a91a6ab95ea00832a93197847f2320455c7f9081be2172396b4e", "generation_seconds_batch": 23.910610068007372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031854674220085144, "target_z": -0.42382812271135556, "ce": 5.998785495758057, "genuineness": 3.9425034523010254, "identity": 0.38401705026626587, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/66e110e0638616fb58e8e6249e287b0ffc24fd61998d656453cd41a4d6e7b442.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": "67673ce01f991f87f59e0fb57e06c33e7bddf9a4fd2461d1fc776cd58cbff1a3", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The keys are on the kitchen table.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c485f899041865c800dd43d9cab2b1bf99d09ef535688a102e4b0669769350d", "generation_seconds_batch": 16.09574150305707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054655179381370544, "target_z": -0.3710937567313072, "ce": 6.332377910614014, "genuineness": 4.293961524963379, "identity": 0.5021611452102661, "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_Sourness/67673ce01f991f87f59e0fb57e06c33e7bddf9a4fd2461d1fc776cd58cbff1a3.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "680340b75b86369eb399bf50ac69babd7ca3a091e19227c651d637c5553ae5ed", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e0807ac0c71e9fd6746d9cbbd0e9a1e6be26649a297179c6c4338d587dc4fa4b", "generation_seconds_batch": 24.00901875901036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08843371272087097, "target_z": -0.29296875350027973, "ce": 6.0146708488464355, "genuineness": 4.2249250411987305, "identity": 0.5252653360366821, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/680340b75b86369eb399bf50ac69babd7ca3a091e19227c651d637c5553ae5ed.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": "680e262f720976f469e14694c9beb1aed2bd6ec568d1c74551bd3518430ac811", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e3eef6baaefeff44593d91e33f243ef20447e5136987e168b2c08e4f5a4dce3e", "generation_seconds_batch": 18.568382801953703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07745568454265594, "target_z": -0.31835939075125885, "ce": 6.125868320465088, "genuineness": 4.293961524963379, "identity": 0.5616738796234131, "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_Sourness/680e262f720976f469e14694c9beb1aed2bd6ec568d1c74551bd3518430ac811.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "682acf2b7003eecf3cc8a1d9ab5ceb38177bb66f9cbc75b92067326ef9adb3b8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3ae15425e60156f83f54eb489a4e9470bea19313e767d686240d59172e71e78a", "generation_seconds_batch": 18.948233003960922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1036340519785881, "target_z": -0.257812503769532, "ce": 6.046441555023193, "genuineness": 4.168440818786621, "identity": 0.4745331406593323, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/682acf2b7003eecf3cc8a1d9ab5ceb38177bb66f9cbc75b92067326ef9adb3b8.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "68772e8c35b3700d7b4325003e9c1ccc011e24fecee36a59a4c5b628562655b9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "69d5ef0824d40f629664d0d52a6106f83ad31e667f30b714255ae6a1327912df", "generation_seconds_batch": 23.50296717695892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28266027569770813, "target_z": 0.15625000646205492, "ce": 6.41180419921875, "genuineness": 4.406930446624756, "identity": 0.4964461624622345, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/68772e8c35b3700d7b4325003e9c1ccc011e24fecee36a59a4c5b628562655b9.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": "68a96e14c86bc39191a4e35cf0c75cb193f93592904770bbef406f1458c4d7b8", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Your message arrived after I had left.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dfcefa0e0b16ea78ec05874cbe58556dcd59b5414093263b97ca259385ce0be8", "generation_seconds_batch": 19.412076186970808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09687834978103638, "target_z": -0.2734374940764497, "ce": 6.372091293334961, "genuineness": 4.093128204345703, "identity": 0.5196939706802368, "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_Sourness/68a96e14c86bc39191a4e35cf0c75cb193f93592904770bbef406f1458c4d7b8.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "68b01df09f0b7776f10a08b3a9ae107d6e743d3ceee0f4c1c170d507c55816f6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cbb0aca98ddde4dc0fc90f7f6235def9c3c6921baf28ae6802cc3eac69b2732d", "generation_seconds_batch": 23.972637524013408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18301360309123993, "target_z": -0.07421875134626144, "ce": 6.09409761428833, "genuineness": 4.300237655639648, "identity": 0.7617864608764648, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/68b01df09f0b7776f10a08b3a9ae107d6e743d3ceee0f4c1c170d507c55816f6.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "69c7e9883c9dd8f39eaf66b7950c4e8ecf55f1494fa6bc506b663ce0bac96a0a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "36578020d1f6ffcfe611a51bd8f06ac1b6c9b81e47902f9ea86fa257821116a3", "generation_seconds_batch": 22.999037294997834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0453660786151886, "target_z": -0.3925781420975203, "ce": 6.205295085906982, "genuineness": 4.7332844734191895, "identity": 0.7520918846130371, "hypothesis": "J'ai trouvé la 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_Sourness/69c7e9883c9dd8f39eaf66b7950c4e8ecf55f1494fa6bc506b663ce0bac96a0a.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": "69cc3e30d6605d9703f6364931c30630fad9d63529e1c7eebaefb57bf955f52f", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2584ba562db870a6e0d0c4715e3a773a14d9a00a6d1cc58bbe1aaa5e4445f863", "generation_seconds_batch": 15.520973699982278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09856727719306946, "target_z": -0.2695312421916836, "ce": 6.09409761428833, "genuineness": 4.344170093536377, "identity": 0.6006203293800354, "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_Sourness/69cc3e30d6605d9703f6364931c30630fad9d63529e1c7eebaefb57bf955f52f.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "6a2a8f2d73f662976315765c5cec77ccc0ae68eb0d7be130da4179d889ee55ce", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fa5012546cf605bd5d8ed1915967c7620da6e199fe1ce5b942d94dd538f4e18f", "generation_seconds_batch": 21.407543204026297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.356205940246582, "genuineness": 4.068024158477783, "identity": 0.5151443481445312, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6a2a8f2d73f662976315765c5cec77ccc0ae68eb0d7be130da4179d889ee55ce.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "6a45d6e70c981497de7a93d6d3e0c6b8c16f73558d41190afecb479ead2ab1cd", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5578f551d443d6d19fdb36641d0e2a744907e4c3b73404a6845833e494b1bc0c", "generation_seconds_batch": 25.389819030067883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08674478530883789, "target_z": -0.29687500538504574, "ce": 6.24500846862793, "genuineness": 4.093128204345703, "identity": 0.388326495885849, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6a45d6e70c981497de7a93d6d3e0c6b8c16f73558d41190afecb479ead2ab1cd.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "57c43aea53ddb0f76d5e8457f56d902b0f7d420626f1ea0bb7cbdf39c336ec6e", "generation_seconds_batch": 19.354454244021326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07998907566070557, "target_z": -0.31250001292410984, "ce": 6.427689552307129, "genuineness": 3.9299514293670654, "identity": 0.3953172564506531, "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_Sourness/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "6ac082208c4c1f756609a1d8e468a097c7959293cecb4068d3a893dee506fc53", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "15ecd691e72525c30bff0ea2ee861c6e1a547d112c863ceb565eaef2877d48e4", "generation_seconds_batch": 22.915424890932627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021721109747886658, "target_z": -0.4472656340199517, "ce": 5.784333229064941, "genuineness": 4.105680465698242, "identity": 0.6768701076507568, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6ac082208c4c1f756609a1d8e468a097c7959293cecb4068d3a893dee506fc53.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "6acda2e4802fdafaf916c964f49025df7ab5b34bdb27ea6a3e295701fed736ed", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "215185aab6a286e0274c0aa8661d53ac7b57b97483a07067aeb9960da738462a", "generation_seconds_batch": 18.752136463997886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05803303420543671, "target_z": -0.36328125296177516, "ce": 5.927301406860352, "genuineness": 4.413206577301025, "identity": 0.6557481288909912, "hypothesis": "J'ai trouvé la 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_Sourness/6acda2e4802fdafaf916c964f49025df7ab5b34bdb27ea6a3e295701fed736ed.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "6af5a70cc35120617b29b3a757971c9e83df48cc7511b1ddde6915165eafc266", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "38a412b76f52697f1b0cd125121f53ddf07eb1ca1cf5956a32d8ad0d65ba7624", "generation_seconds_batch": 17.57119634002447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10532297939062119, "target_z": -0.253906251884766, "ce": 5.645336627960205, "genuineness": 4.344170093536377, "identity": 0.5050289630889893, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6af5a70cc35120617b29b3a757971c9e83df48cc7511b1ddde6915165eafc266.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "6b860889dc1e80c0d27fa57713d4be65ac7d07ae7f5efb99f4bf8f3dc562a985", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "69700f2d5bcf59acda43ee4078b8f6e4f93156a8b6840d5ad8198f3fca70d222", "generation_seconds_batch": 23.01965280494187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28266027569770813, "target_z": 0.15625000646205492, "ce": 5.982900142669678, "genuineness": 3.7291181087493896, "identity": 0.3738827109336853, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6b860889dc1e80c0d27fa57713d4be65ac7d07ae7f5efb99f4bf8f3dc562a985.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "257ed06c773a47e926daef99d817fea302c8d1624dea2238dac6d410aae53c58", "generation_seconds_batch": 19.516083715949208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13741257786750793, "target_z": -0.17968751777065103, "ce": 6.24500846862793, "genuineness": 4.6705241203308105, "identity": 0.6106513738632202, "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_Sourness/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.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": "6bb7e29f8bfac6d3a3e2a803335ef8345973bcc56224db4f506645ebce467715", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "060ca1a7864a88876a87359de367e7c0640bbc2da68d00ecda61b22b17085ce2", "generation_seconds_batch": 14.520992433070205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1576797068119049, "target_z": -0.1328124951534588, "ce": 6.109982967376709, "genuineness": 4.218649387359619, "identity": 0.6268558502197266, "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_Sourness/6bb7e29f8bfac6d3a3e2a803335ef8345973bcc56224db4f506645ebce467715.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": "6be266abbcbd14db7b00ef1adb2d2c298ca66a4932bda1e7550fe38f099a2ef8", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce8186c7a44ae041353321ab7d14f33bbf9c4247748e3fe33526e0183a4b4b49", "generation_seconds_batch": 22.835090122069232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6609798669815063, "target_z": 1.031250084006714, "ce": 6.09409761428833, "genuineness": 3.9927117824554443, "identity": 0.7326650619506836, "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_Sourness/6be266abbcbd14db7b00ef1adb2d2c298ca66a4932bda1e7550fe38f099a2ef8.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "6bf75a4faec2c29bd115c41867ee71435be81ddf38017d85acc38e66186bba73", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a70a306fdeddae2767acbb243d0e6b4874e24c7de4a38587351428d85a93458f", "generation_seconds_batch": 25.178357504075393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1744134426116943, "target_z": 2.2187498298325536, "ce": 6.062326908111572, "genuineness": 4.293961524963379, "identity": 0.5886147022247314, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6bf75a4faec2c29bd115c41867ee71435be81ddf38017d85acc38e66186bba73.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "6cf041d7649652fe49df6c3e352990c1240bd3ecea4480aa98e23f1d7e6d2fd9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bc5bae1d84d1e17a3236495a244b3ffbb9f4b9e371d88b0b7c260818dfb4c7ae", "generation_seconds_batch": 20.340080408961512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17456896603107452, "target_z": -0.09375001077009153, "ce": 5.95112943649292, "genuineness": 3.7667744159698486, "identity": 0.26862895488739014, "hypothesis": "The 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_Sourness/6cf041d7649652fe49df6c3e352990c1240bd3ecea4480aa98e23f1d7e6d2fd9.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": "6d04be08321100aae636430aaedaa47399e613fe2947c939851994f7d51df414", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0d10db1e542dcdcc377e3894e955ccd4a844e228329651aed1f22a68ca2c8bc0", "generation_seconds_batch": 24.233708895975724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08336693048477173, "target_z": -0.3046875091545778, "ce": 6.173524379730225, "genuineness": 4.13078498840332, "identity": 0.4179863929748535, "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_Sourness/6d04be08321100aae636430aaedaa47399e613fe2947c939851994f7d51df414.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "6dfbfc7607ececd94cdcd566e77624e3b96f34f3796ba32536f2fd5bb6f07097", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bee35394945a268721f4f0a496c596591dc8af10cf2611c97d4b97fe957e2584", "generation_seconds_batch": 26.48452864808496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06141088902950287, "target_z": -0.35546874919224314, "ce": 6.157639026641846, "genuineness": 4.444586753845215, "identity": 0.29731684923171997, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6dfbfc7607ececd94cdcd566e77624e3b96f34f3796ba32536f2fd5bb6f07097.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "6e450dd0203f7e44d812d2ed91c022a8a2e9e350c2e6c0a2c56276751b0e810d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b938734edd4bc9ce95901ac6613c90460743308b7ea8cf0bacf9912cad884886", "generation_seconds_batch": 16.347756145056337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03485792875289917, "target_z": -0.5781250032310274, "ce": 5.784333229064941, "genuineness": 3.8797430992126465, "identity": 0.4036060571670532, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6e450dd0203f7e44d812d2ed91c022a8a2e9e350c2e6c0a2c56276751b0e810d.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "6f0ef012b8c9f4cb5125aa13afd8d42b6f63254700246e319a94fae21a3efba5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b99506948108e54b6fa47b7dcedafaa27a2b0e4d4cd78127327943823cb8f0c8", "generation_seconds_batch": 26.347491367021576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.228459119796753, "target_z": 2.3437498901450664, "ce": 6.0146708488464355, "genuineness": 3.798154592514038, "identity": 0.16222532093524933, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6f0ef012b8c9f4cb5125aa13afd8d42b6f63254700246e319a94fae21a3efba5.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "6f58f1c628d2a79a57208d9504d13b7b69dbee9cccf4779c3b72301503ffaf78", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3658664e6637133ca8613bc8ac3eb2fa98b98a8fce1f3622a54965ae6d4a1469", "generation_seconds_batch": 24.142467778059654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033543601632118225, "target_z": -0.41992187082658955, "ce": 5.6254801750183105, "genuineness": 3.9173994064331055, "identity": 0.6516793370246887, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6f58f1c628d2a79a57208d9504d13b7b69dbee9cccf4779c3b72301503ffaf78.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": "6f8ff8af08188f68670f039156df779672e3ab73cfe30c426bca21dddc30f1f5", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f63d7bbb0badceb683225cd35e56d847515fd72308686e8f481f78f6ab177055", "generation_seconds_batch": 24.431412128033116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06732213497161865, "target_z": -0.34179686759556205, "ce": 6.316492557525635, "genuineness": 4.607763767242432, "identity": 0.46350011229515076, "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_Sourness/6f8ff8af08188f68670f039156df779672e3ab73cfe30c426bca21dddc30f1f5.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": "6f9429f24350c10915be98ae98664b8ab0be4783a5a7c103fa65962c9fe68743", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "92f46efcf32b3bca606b6102a7bcb96604e4116efa81129afd3ba43d6c7dd5b6", "generation_seconds_batch": 14.472811475978233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08167800307273865, "target_z": -0.30859376103934383, "ce": 5.990842819213867, "genuineness": 3.911123275756836, "identity": 0.3281623125076294, "hypothesis": "Ik schreef het nummer op de envelop, lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6f9429f24350c10915be98ae98664b8ab0be4783a5a7c103fa65962c9fe68743.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "6fd25e8b239b329095a978eec02a24af93d1cad398fda301d4881324522614f4", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4c78d24cb5103aea6584170b92726ed0abe61675963cf57c516f11b6f6e04bd9", "generation_seconds_batch": 23.29144824494142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032699137926101685, "target_z": -0.42187499676897255, "ce": 5.359400749206543, "genuineness": 3.653805732727051, "identity": 0.5379123687744141, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/6fd25e8b239b329095a978eec02a24af93d1cad398fda301d4881324522614f4.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "700766750d8bc8b23c79a894d9f52ac8a8ea15d5f15bfd605ef99e8b16c0fcb6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ef8891f587eb1527e2dc541d82f5ee8c378c22eb073b1869f36b5d2ccce5cc15", "generation_seconds_batch": 23.049762167036533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054655179381370544, "target_z": -0.3710937567313072, "ce": 6.125868320465088, "genuineness": 4.068024158477783, "identity": 0.3971010446548462, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/700766750d8bc8b23c79a894d9f52ac8a8ea15d5f15bfd605ef99e8b16c0fcb6.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": "702289c8a1aa452e62265f18367f87312160e6df829536a3f7b7704da9c532c6", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc935f3916084c803562d9d3855f529b0d60b544a056d0bd113c68389d0813f9", "generation_seconds_batch": 14.407023231964558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8231167793273926, "target_z": 1.4062499892299085, "ce": 6.117925643920898, "genuineness": 4.030367851257324, "identity": 0.5730239152908325, "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_Sourness/702289c8a1aa452e62265f18367f87312160e6df829536a3f7b7704da9c532c6.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "7068be7a59e13e01009e0a06ea2501622b7211de63fef53c84f490292f3b4a15", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a82baeb8c7bc450953e35184309ab2fb05957030d7508f1a99b57a3c738cda70", "generation_seconds_batch": 26.291464239009656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03945484757423401, "target_z": -0.40624998922990846, "ce": 6.2767791748046875, "genuineness": 4.325342178344727, "identity": 0.2613102197647095, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7068be7a59e13e01009e0a06ea2501622b7211de63fef53c84f490292f3b4a15.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "707ef5737787c41118aef6f7cb296cf6cb549c868fe0c37cd461bc63096201f3", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d1e03d9df0d40d77c01fc81dc1c1a884705f948894ce750c557147674534347c", "generation_seconds_batch": 24.987188157974742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3696399927139282, "target_z": 0.35742187513462614, "ce": 5.847874641418457, "genuineness": 3.873466968536377, "identity": 0.6424864530563354, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/707ef5737787c41118aef6f7cb296cf6cb549c868fe0c37cd461bc63096201f3.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "70da7445b652b020be63b1f68ce9fad0052268c002f328a5ab3d720f50548d63", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f91ad64ec1c2f35df6de7f29ecdcc6fbcd56653e8c8b5de40a1cf39e643fb2dd", "generation_seconds_batch": 25.051864368026145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1036340519785881, "target_z": -0.257812503769532, "ce": 6.117925643920898, "genuineness": 4.055472373962402, "identity": 0.786956787109375, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/70da7445b652b020be63b1f68ce9fad0052268c002f328a5ab3d720f50548d63.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "711efc3939de7de47395d8f02cc583e6b6aa0c6602e918d628096ec9c7188481", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "868a82d8ffd9d00116fe5208e535e0e207344e39909ce0d2611cdc04ccc609b2", "generation_seconds_batch": 26.529815627960488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4041075706481934, "target_z": 2.7500000861607323, "ce": 5.736677646636963, "genuineness": 3.6412534713745117, "identity": 0.49822473526000977, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/711efc3939de7de47395d8f02cc583e6b6aa0c6602e918d628096ec9c7188481.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "71e04f5759da271ae9657f4b1cb5056d91ee34155951fdfcb4bbb104555e30ab", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cfb36fe9f33ec7e4c3e72fd672bc6c99f9128de67924a7318e8846da8ca9f22b", "generation_seconds_batch": 16.322845098911785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0495883971452713, "target_z": -0.38281251238560526, "ce": 6.213237762451172, "genuineness": 4.344170093536377, "identity": 0.4654328227043152, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/71e04f5759da271ae9657f4b1cb5056d91ee34155951fdfcb4bbb104555e30ab.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "71ff90d7d67e5d8429a46502248ff6205635577a9262fbcac66c7560d2a73ac7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9b32e70aab99673729a530d3fe6b066331efd4629e7684ed5fbeeb8ca5d0b757", "generation_seconds_batch": 23.09731155296322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022565573453903198, "target_z": -0.44531250807756867, "ce": 5.927301406860352, "genuineness": 4.080576419830322, "identity": 0.47424229979515076, "hypothesis": "J'ai trouvé la 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_Sourness/71ff90d7d67e5d8429a46502248ff6205635577a9262fbcac66c7560d2a73ac7.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": "72008c9a380f09032be43c98600b6835bf21fead9fded1a3d58b60aed183f1c9", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4e9c3f406319695bfc8ea0fdb96f04e56aff4269c7b09f5a29deeb59d2d80be", "generation_seconds_batch": 26.718694998067804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12896795570850372, "target_z": -0.19921874273018822, "ce": 6.086154937744141, "genuineness": 4.13078498840332, "identity": 0.645044207572937, "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_Sourness/72008c9a380f09032be43c98600b6835bf21fead9fded1a3d58b60aed183f1c9.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "72ac1ecdaad4fa2f407a75e34f15fecd798d61788804839449cda14bbb33026c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b5a5b3ad80e827a673b1232d63db5abd04cdef9d009b321ad58c1a37a842a233", "generation_seconds_batch": 24.868951832060702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14416828751564026, "target_z": -0.16406251023158694, "ce": 6.1894097328186035, "genuineness": 4.287685871124268, "identity": 0.6553328037261963, "hypothesis": "De deur 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_Sourness/72ac1ecdaad4fa2f407a75e34f15fecd798d61788804839449cda14bbb33026c.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "73a79658aae4c61acc44e5abd82988f1c34027731dfbbab8fd291014125498af", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b0306556f8cbddc32a018e63e9f953e82b42f54858474596a41a5e0cf3008bfb", "generation_seconds_batch": 21.537630146951415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.681091547012329, "target_z": 3.390625119548016, "ce": 5.895530700683594, "genuineness": 3.5471129417419434, "identity": 0.20351102948188782, "hypothesis": "Ik 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_Sourness/73a79658aae4c61acc44e5abd82988f1c34027731dfbbab8fd291014125498af.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "750f2a6b7ae15ed82bbccfacdbedcc83da660b1a1cc6bb1ee2234874ca4250b6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e763b77886cac5869be64cfa46495e18efcd95e42237a409e0a108a1d9fd74f6", "generation_seconds_batch": 22.89211208699271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0056763142347335815, "target_z": -0.4843749924609359, "ce": 6.157639026641846, "genuineness": 4.293961524963379, "identity": 0.6424713134765625, "hypothesis": "J'ai trouvé la 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_Sourness/750f2a6b7ae15ed82bbccfacdbedcc83da660b1a1cc6bb1ee2234874ca4250b6.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "7519a349ca1062f9ca408676ed8ab6a812310c4ec820188f57534fa788b1ef2f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "63550612566bf5cad4e43d7e50177690eb1c622d1c8aa5fd86721ea618aa2629", "generation_seconds_batch": 23.5877281910507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8366281986236572, "target_z": 1.4375000043080366, "ce": 5.808161735534668, "genuineness": 3.5690791606903076, "identity": 0.5198022723197937, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7519a349ca1062f9ca408676ed8ab6a812310c4ec820188f57534fa788b1ef2f.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "7533c85c00e584792ee930cbdaeac73f438e651dc6c9b9506e4b56b6c3527d86", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9e74f7734ea39dcf94e356f963174b5cb70a81d3fe59c39bae17efcdb17c2e3a", "generation_seconds_batch": 23.236022733035497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1762578934431076, "target_z": -0.08984375888532552, "ce": 5.982900142669678, "genuineness": 4.105680465698242, "identity": 0.5526009798049927, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7533c85c00e584792ee930cbdaeac73f438e651dc6c9b9506e4b56b6c3527d86.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "75756ee3170e3f8cd19137de5f20c758a762e44958fb2dfacf03c8bc43ddfca5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1a90999067a5f4daf2ce5f11bc4730055f9dfb3774a7fb181152cd21d14388e1", "generation_seconds_batch": 16.83630693005398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 6.260893821716309, "genuineness": 4.20609712600708, "identity": 0.12403778731822968, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/75756ee3170e3f8cd19137de5f20c758a762e44958fb2dfacf03c8bc43ddfca5.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "7618733a6c5503ffba7f235fa07c1697e3f774dedb5de2f3f130221e99c65103", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9598690f93f2ef19e8e660cdc2f849c45cc121349b81f21eacaeb8ec5a8872a7", "generation_seconds_batch": 18.0145450810669, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2505706548690796, "target_z": 0.08203122065150059, "ce": 5.903473377227783, "genuineness": 4.281409740447998, "identity": 0.51873779296875, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7618733a6c5503ffba7f235fa07c1697e3f774dedb5de2f3f130221e99c65103.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "762616c259b94b767eb8345db5e47463df8e5d098a04a7bd3b5fd41f5403054d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5c43fe2b67a0cdd70fe23df8092bb96d546fc51218b373e769c8047c6d8f33fa", "generation_seconds_batch": 21.975240239989944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05803303420543671, "target_z": -0.36328125296177516, "ce": 5.959072113037109, "genuineness": 4.406930446624756, "identity": 0.5839738845825195, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/762616c259b94b767eb8345db5e47463df8e5d098a04a7bd3b5fd41f5403054d.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "765f06382daafcb3679d2d41042f0349a71db74ef42603f53a17520116d0e062", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a445bf09ee6e96ad5fadaddab6ebaa7f7e9307fca278458908afb84480d5e5d8", "generation_seconds_batch": 23.989061560947448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05972196161746979, "target_z": -0.35937500107700915, "ce": 5.77639102935791, "genuineness": 4.2249250411987305, "identity": 0.4780365526676178, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/765f06382daafcb3679d2d41042f0349a71db74ef42603f53a17520116d0e062.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": "76ce08556e5990abef9e6f010070b6101a687703821aa957458b83f1e1e88cdb", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "92031d8031aa8cc77f92ec8910d7ef505002c49d12b48f3f64b39bba46f9e479", "generation_seconds_batch": 19.199119925964624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09350049495697021, "target_z": -0.2812499978459817, "ce": 6.340320587158203, "genuineness": 4.519899368286133, "identity": 0.6402924060821533, "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_Sourness/76ce08556e5990abef9e6f010070b6101a687703821aa957458b83f1e1e88cdb.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "778002de812e678ed9bf555a39b328c7785ddebc5d920ce57160287a889a095d", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5426b296091dcc100ffe61f51d5d506b03cf98ded8f39cd2f64f96e145fb599b", "generation_seconds_batch": 17.678999888012186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04367716610431671, "target_z": -0.39648435951799343, "ce": 6.117925643920898, "genuineness": 4.306513786315918, "identity": 0.44928568601608276, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/778002de812e678ed9bf555a39b328c7785ddebc5d920ce57160287a889a095d.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "81bf106914578be194b942f9ce0e4374eb23a4abe72165eeae3122915e175f29", "generation_seconds_batch": 17.10577444906812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08590032160282135, "target_z": -0.29882813132742875, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.6349645853042603, "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_Sourness/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.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": "77da79c709a026688350ef88f37bbad8b7954d0df24893e722683ffab58434db", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "706d3359fb2c70836a9898f7707919a5037adbbc3812a38888667ddbd55c4ac7", "generation_seconds_batch": 26.718694998067804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12727902829647064, "target_z": -0.20312499461495423, "ce": 6.006728172302246, "genuineness": 4.15588903427124, "identity": 0.6848632097244263, "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_Sourness/77da79c709a026688350ef88f37bbad8b7954d0df24893e722683ffab58434db.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "77e74d9aa574f522f0139ab61bc4f7e4c8e6c227cfe999ba4a3b5a867de1971c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "82f524e314a1daa77082ba5b964b0f3265194d43353111307999cac3019975df", "generation_seconds_batch": 27.195999452029355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19145824015140533, "target_z": -0.05468749192243135, "ce": 5.661221981048584, "genuineness": 4.356721878051758, "identity": 0.5222761631011963, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/77e74d9aa574f522f0139ab61bc4f7e4c8e6c227cfe999ba4a3b5a867de1971c.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "788013b8f68591eac3b346d9ee479c64c6d2333bbf86f26dcd984856eb6c2838", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1ff4967d762a80dddb12acb3bebec7cbd7df65b70163d1526b2c50c1ad402503", "generation_seconds_batch": 22.377107089036144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22861462831497192, "target_z": 0.03125001507812814, "ce": 5.990842819213867, "genuineness": 4.143336772918701, "identity": 0.6256605982780457, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/788013b8f68591eac3b346d9ee479c64c6d2333bbf86f26dcd984856eb6c2838.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "7881302946850b294a541ba90d0f99b927d86e62546beb35fd5be9ae84281000", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b8a98ed689d2dc357b950902f89c4743db592b98b7f29875ac603cbbc7f1ed5a", "generation_seconds_batch": 24.502812259015627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007835105061531067, "target_z": -0.515625007539064, "ce": 5.927301406860352, "genuineness": 4.143336772918701, "identity": 0.5014692544937134, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7881302946850b294a541ba90d0f99b927d86e62546beb35fd5be9ae84281000.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "78876fe0df925e905b3615070030f8d4e1ea97c1e0782a6d389e69900a9b289e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "419b79f3406c492ebf15ff1bc9d86be8d89997e5b41ebbaf66c0b272084cf7f5", "generation_seconds_batch": 21.737091127899475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020032182335853577, "target_z": -0.4511718859047177, "ce": 6.125868320465088, "genuineness": 4.193545341491699, "identity": 0.4131195843219757, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/78876fe0df925e905b3615070030f8d4e1ea97c1e0782a6d389e69900a9b289e.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "be3480e22bbe985731632798522d3fccc8804397c1e26488ca6c45ba6dde73ec", "generation_seconds_batch": 16.177798233926296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08505585789680481, "target_z": -0.3007812572698118, "ce": 6.252951145172119, "genuineness": 4.21237325668335, "identity": 0.48660194873809814, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "79ed1405cc6bb8985e32d15e374213eb643c2cfd086e7ec37daf839e840d3901", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8750bc483af9c13c5020f38b5a90646b507db0268c853429241975aef83c5d37", "generation_seconds_batch": 26.228021824965253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06985552608966827, "target_z": -0.33593748976841303, "ce": 5.903473377227783, "genuineness": 4.055472373962402, "identity": 0.467000812292099, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/79ed1405cc6bb8985e32d15e374213eb643c2cfd086e7ec37daf839e840d3901.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "7ad557192f65cbfe9aad06427b7f5e9dd89e2c669ad7467b89ce1f59a86ded07", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dc953d28c9d44fc054fba473d09532a03e660b51ca8f5b3af23676cb40bf64be", "generation_seconds_batch": 23.384512135991827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.028102219104766846, "target_z": -0.5624999956919634, "ce": 6.332377910614014, "genuineness": 4.582659721374512, "identity": 0.533212423324585, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7ad557192f65cbfe9aad06427b7f5e9dd89e2c669ad7467b89ce1f59a86ded07.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": "7aeedd1487d7c4763f8beb7d78c34d3e33b7b695ce812f9a73a9b26551ec10d9", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54ec5a620c9eb58f18041e24fd1f7edc0873b529f6f71ed8c326c2d4a01ef4de", "generation_seconds_batch": 15.45013392099645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15599077939987183, "target_z": -0.13671874703822484, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.5645079612731934, "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_Sourness/7aeedd1487d7c4763f8beb7d78c34d3e33b7b695ce812f9a73a9b26551ec10d9.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "7b5b56d064a97ec2762dcb87e499a26bb9626f9ba95138fc9c25254d479dc76e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a0bcac26da05c38c9abacd7a40723304621c54b158f5f76c956747725be26d34", "generation_seconds_batch": 25.322767712990753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7623154520988464, "target_z": 1.2656250592355034, "ce": 6.086154937744141, "genuineness": 3.973883628845215, "identity": 0.5917111039161682, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7b5b56d064a97ec2762dcb87e499a26bb9626f9ba95138fc9c25254d479dc76e.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "7bc5ac005bd36b9830c90f3c53834510ceecd866689d16a5831a63337eddffe8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6d1b2041212a1e07c7e5060aba1d92309c2e018993c786c4be72caac99830074", "generation_seconds_batch": 17.57119634002447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015809863805770874, "target_z": -0.4609375156166327, "ce": 6.0305562019348145, "genuineness": 4.532451152801514, "identity": 0.6937090158462524, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7bc5ac005bd36b9830c90f3c53834510ceecd866689d16a5831a63337eddffe8.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "7bc9136acf52c059e1c8d29cfe4bf75df835d0bd89663616eab0e5e43cbf1aa7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cbd60726700f432cca43b95bf06612ed70ad2729d743752da26ac97fcf1b8093", "generation_seconds_batch": 23.305545709910803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016279742121696472, "target_z": -0.5351562669628942, "ce": 6.348263263702393, "genuineness": 4.381826400756836, "identity": 0.5171806812286377, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7bc9136acf52c059e1c8d29cfe4bf75df835d0bd89663616eab0e5e43cbf1aa7.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "7c61a9205428c20b1220620e24bad8c110839ce2a4824bb9425f9e5b7ea097c1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0966ee7fd1261e191c26b416ab6a403b83efe32f62d69797a466beadbd81a097", "generation_seconds_batch": 24.514551364001818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23874817788600922, "target_z": 0.05468749192243135, "ce": 6.0305562019348145, "genuineness": 4.105680465698242, "identity": 0.559764564037323, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7c61a9205428c20b1220620e24bad8c110839ce2a4824bb9425f9e5b7ea097c1.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "7c9ecc2235fc56dcbd36351fa5ceecbd2b367629c18ec23606fff180c485e316", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b5e908468bc2d8d79355b48049af41fe0df5d1c4c64718f02f6b156c553725a3", "generation_seconds_batch": 30.175721811014228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5562663674354553, "target_z": 0.7890624671512209, "ce": 5.919358730316162, "genuineness": 4.074300289154053, "identity": 0.3347868323326111, "hypothesis": "J'ai trouvé la 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_Sourness/7c9ecc2235fc56dcbd36351fa5ceecbd2b367629c18ec23606fff180c485e316.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "7d0e31bdb33df32ea9dcd9132010118c398f1511dda42a3a5bade431e1ce2b4a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29c6bbbca13066e98c9598574d9091d7824021891aa61b8e1e7b34ccb48aad6a", "generation_seconds_batch": 21.799316844902933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13403472304344177, "target_z": -0.18750002154018305, "ce": 6.141753673553467, "genuineness": 4.068024158477783, "identity": 0.5487440228462219, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7d0e31bdb33df32ea9dcd9132010118c398f1511dda42a3a5bade431e1ce2b4a.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "7d2e4dc32f6ffe6bd1417739c77405390c2c4cf5da72fd285392afd22d3aab9e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "232472f87e0c723ae1e32b46092896584e4ccc7b85ba2601bf6a4fb8f71b6de6", "generation_seconds_batch": 17.518879274954088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09012264013290405, "target_z": -0.2890625016155137, "ce": 5.617537498474121, "genuineness": 4.306513786315918, "identity": 0.6372120976448059, "hypothesis": "J'ai trouvé la 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_Sourness/7d2e4dc32f6ffe6bd1417739c77405390c2c4cf5da72fd285392afd22d3aab9e.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": "7d2f94abebe1bea104129081769469133efe598059ebf165601c4019fe985b48", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9cfca5115618172eb21b820d138ff78dc6013bc3803f38799ea6c4479e291457", "generation_seconds_batch": 14.463694814941846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6846247911453247, "target_z": 1.0859374725362667, "ce": 6.0146708488464355, "genuineness": 4.124508857727051, "identity": 0.8115582466125488, "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_Sourness/7d2f94abebe1bea104129081769469133efe598059ebf165601c4019fe985b48.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "7da9455c8bfda2fb6dc17b621b34d7225603f6022b9363c9858ab437f6e0f424", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5bca18eeb0e24cc1f08323e5d42b52fafdd0ab84b06d76d8c775e8ab74dd3ba1", "generation_seconds_batch": 24.223486138042063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08674478530883789, "target_z": -0.29687500538504574, "ce": 6.1020402908325195, "genuineness": 3.810706615447998, "identity": 0.3335457444190979, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7da9455c8bfda2fb6dc17b621b34d7225603f6022b9363c9858ab437f6e0f424.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": "7e0e0273f13dedca62f69d09dc38096e9d2f9310c9111190aaee412a5abbd588", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b27fb59a8a18900415ce28045dc18fbe086944e31f711704a275263a1cbe78ad", "generation_seconds_batch": 19.573650588979945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033543601632118225, "target_z": -0.41992187082658955, "ce": 6.3641486167907715, "genuineness": 4.344170093536377, "identity": 0.6750890612602234, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier, neben dem Hohnbücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7e0e0273f13dedca62f69d09dc38096e9d2f9310c9111190aaee412a5abbd588.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "7f6f15e77bfa8bf4b6fbd5e3c71a32be5008a69accd0a5deab81a7946fce939a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c593007282144175d6ab0058a0647d25127eb3d05cf1ed082a7067f22e32d9ed", "generation_seconds_batch": 27.76792336406652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05972196161746979, "target_z": -0.35937500107700915, "ce": 5.935244083404541, "genuineness": 4.432034492492676, "identity": 0.6014912128448486, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7f6f15e77bfa8bf4b6fbd5e3c71a32be5008a69accd0a5deab81a7946fce939a.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2632e15870a0d3781213961e4db6182808bf1b9d42416a281c8afb3f468b51db", "generation_seconds_batch": 15.296974314027466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06985552608966827, "target_z": -0.33593748976841303, "ce": 6.38003396987915, "genuineness": 4.532451152801514, "identity": 0.4944082498550415, "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_Sourness/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "7ffdef1e7140b5ceb31f17c3a5cf3a8e00642c5378450125314c70c23b5c1463", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a4098d109356475136c4e1d52689ef524b8decabe8f169459c39b2808654aac7", "generation_seconds_batch": 18.378422364010476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04198823869228363, "target_z": -0.40039061140275944, "ce": 6.09409761428833, "genuineness": 4.331617832183838, "identity": 0.7238858938217163, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/7ffdef1e7140b5ceb31f17c3a5cf3a8e00642c5378450125314c70c23b5c1463.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": "801ae6ca4e721c9ee2a4a3083922eeb441a15d99c95adf60e401d044deec9c2c", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94d5beaf3706e7f7e603c365f39114cd04f04fa28a84ae796d08f1a57ea2f8e6", "generation_seconds_batch": 22.835090122069232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2014362812042236, "target_z": 2.2812498599888102, "ce": 6.117925643920898, "genuineness": 3.9550557136535645, "identity": 0.6002987623214722, "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_Sourness/801ae6ca4e721c9ee2a4a3083922eeb441a15d99c95adf60e401d044deec9c2c.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "8033b9a2fcfe786b0a5a964e81d5f17e4c104c4efa0e0e83db5775aacf9eafe8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ca03b418a59eb9865cdcd8d4f117f1ffe5488b1d1d771f1d866a590da876b99d", "generation_seconds_batch": 24.071341499919072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1036340519785881, "target_z": -0.257812503769532, "ce": 6.229123115539551, "genuineness": 4.256305694580078, "identity": 0.7494915723800659, "hypothesis": "Ik 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_Sourness/8033b9a2fcfe786b0a5a964e81d5f17e4c104c4efa0e0e83db5775aacf9eafe8.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "621f7823d542d05f04b5bdc4364134fdb92b92c675574ef0cf853aeb8b924568", "generation_seconds_batch": 18.040136993979104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07154445350170135, "target_z": -0.332031237883647, "ce": 6.1894097328186035, "genuineness": 4.469690799713135, "identity": 0.7490144371986389, "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_Sourness/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.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": "80ec8b7e273af9a6c932647465ab775debe68431b20c8aa43b1fa6d278031a1c", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e40e7acb86171817d25b3a37eb0297f148f6512b69b87549b95f836b60a692d3", "generation_seconds_batch": 14.463694814941846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1676578521728516, "target_z": 2.203125098007833, "ce": 6.252951145172119, "genuineness": 3.948779582977295, "identity": 0.5466587543487549, "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_Sourness/80ec8b7e273af9a6c932647465ab775debe68431b20c8aa43b1fa6d278031a1c.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "81bafa1e4cc83c16e23b6526232daf634e40c6e39cb3886b06489906fb78210c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6e2977c010b0d3b3a7e966fa9c0c5c6c861855249f37b35cd0712b0fa9a956f6", "generation_seconds_batch": 22.478088643052615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.532465934753418, "target_z": 3.0468749536886066, "ce": 5.3792572021484375, "genuineness": 3.773050308227539, "identity": 0.07115929573774338, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/81bafa1e4cc83c16e23b6526232daf634e40c6e39cb3886b06489906fb78210c.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "81e0ebf0455aeef4a9b346c3bb18a2e96bbe9c35cbba920786c7e3df613a33fc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "00e0c1be775bc506e8ca51d1747e6e2ee004526253bc293ab8c936ee86927950", "generation_seconds_batch": 22.155616548960097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12559010088443756, "target_z": -0.20703124649972024, "ce": 6.109982967376709, "genuineness": 4.494794845581055, "identity": 0.6449381113052368, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/81e0ebf0455aeef4a9b346c3bb18a2e96bbe9c35cbba920786c7e3df613a33fc.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "82ed95583139d4c00b60c18b4da194221ce6a037ee842ed404be1bfc2489577d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "67e6c5844bdba4ff294c4413fa5375efd0d09661d474deda388a8bd78a60629f", "generation_seconds_batch": 21.614174754009582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08590032160282135, "target_z": -0.29882813132742875, "ce": 6.086154937744141, "genuineness": 4.281409740447998, "identity": 0.5484670400619507, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/82ed95583139d4c00b60c18b4da194221ce6a037ee842ed404be1bfc2489577d.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "83233c8419b2bdc7103d752261af48d76cc734865b6d6b175071be49147dedea", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3e8d0958ae9a8da7907f3d88db0e38d586f3f91b6090041c7b1b637a0b4fada0", "generation_seconds_batch": 18.633595627034083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11630100011825562, "target_z": -0.22851563186593335, "ce": 6.054384231567383, "genuineness": 4.720732688903809, "identity": 0.6042474508285522, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/83233c8419b2bdc7103d752261af48d76cc734865b6d6b175071be49147dedea.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "835573d98295884640f6a6e2b00706615a510c007d103d324e75da885c9e0fdf", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "99270884e5d3519dc206c1634621cfc2c7ab39aa0d7429bec6336d81c05023d0", "generation_seconds_batch": 22.81291829806287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006520777940750122, "target_z": -0.4824218665185529, "ce": 6.372091293334961, "genuineness": 4.281409740447998, "identity": 0.5570569634437561, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/835573d98295884640f6a6e2b00706615a510c007d103d324e75da885c9e0fdf.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "83d09178dc242b25f1694be30f9ab2d39613cad83fa776222dc567999241a5bb", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a5305918fe453f51c88b043018abbfeaa1957ef4c4306276ccc6c03916d90764", "generation_seconds_batch": 22.504724208964035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.264926552772522, "target_z": 0.11523439613630462, "ce": 6.252951145172119, "genuineness": 4.532451152801514, "identity": 0.588303804397583, "hypothesis": "Ik heb een klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/83d09178dc242b25f1694be30f9ab2d39613cad83fa776222dc567999241a5bb.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "844cdec82a7db806e0399a95b545481eecf94cd1bdd2c2be37585b00f02cb8e5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e4142f0a85294d9f5c2393ccc417da93e2c4d58fa46bda9e2f4ad22dd3ab043b", "generation_seconds_batch": 21.778999811969697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6066231727600098, "target_z": 5.531249773828078, "ce": 5.115163326263428, "genuineness": 3.4215922355651855, "identity": 0.15549613535404205, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/844cdec82a7db806e0399a95b545481eecf94cd1bdd2c2be37585b00f02cb8e5.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "8452ab7634ef2e9d05ad33ac10dd631ec61b76049840fd944c2a0bb8ba484f4d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "efeee392f1eb1ac254e6d19e12c9b24af123e26d06b7da2066668710bbe079e0", "generation_seconds_batch": 23.20115579292178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07830014824867249, "target_z": -0.31640626480887585, "ce": 5.258131504058838, "genuineness": 3.8671910762786865, "identity": 0.5523393154144287, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8452ab7634ef2e9d05ad33ac10dd631ec61b76049840fd944c2a0bb8ba484f4d.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": "8534be3de1bcb75ce9b006e597e5cc8137a8a29ba1ae5020d1c47330f249a1a9", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The road turns left behind the bridge.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bfd32a4cfacda4665fada391762f923b637eacc72c3863bed346d0f29061ca98", "generation_seconds_batch": 15.790321650914848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14585721492767334, "target_z": -0.16015625834682093, "ce": 6.348263263702393, "genuineness": 4.036643981933594, "identity": 0.2620590031147003, "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_Sourness/8534be3de1bcb75ce9b006e597e5cc8137a8a29ba1ae5020d1c47330f249a1a9.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": "858c402cfac0dd5ef7aab8814e08f223d68ec01ff8da17076df569f2adec47e1", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59bd2e1ee9a4afce0bfe99c5b7eaf708db104df24df3ab97f7821e532c7d7f39", "generation_seconds_batch": 16.60646884702146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11714546382427216, "target_z": -0.22656250592355034, "ce": 6.09409761428833, "genuineness": 4.143336772918701, "identity": 0.5062718391418457, "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_Sourness/858c402cfac0dd5ef7aab8814e08f223d68ec01ff8da17076df569f2adec47e1.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "85935259a8cbd632a9035f55f90243ae740fc6965f6c37a1d2c75a5bf7721b15", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6983b9fd0ec0a6ee33c009ae16e1ef30f7b4448b521dde31abce1b22ad1a4f05", "generation_seconds_batch": 24.110933082993142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09012264013290405, "target_z": -0.2890625016155137, "ce": 5.967014789581299, "genuineness": 4.394378662109375, "identity": 0.6079241037368774, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/85935259a8cbd632a9035f55f90243ae740fc6965f6c37a1d2c75a5bf7721b15.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "85df9f8627e2961ed37bf5aee0b1cd141bdfbcea4e769b935350b06db1496300", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d098504d1103a0ebcb33f5e5d597e12c74f04ba2cca5c1f5058f7fb0d430edf8", "generation_seconds_batch": 25.787841791054234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11376761645078659, "target_z": -0.23437499246093593, "ce": 6.125868320465088, "genuineness": 4.024092197418213, "identity": 0.5377981662750244, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/85df9f8627e2961ed37bf5aee0b1cd141bdfbcea4e769b935350b06db1496300.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "8605999df9330ed0ef25bddf50cfbf996a9865f2eb16cd3c3712d9e1737f9a18", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "55371f7ae2ab43f5650a5b69f8706809d913a13218a7442157ded17856dcaa04", "generation_seconds_batch": 25.160149175091647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1001007556915283, "target_z": 2.046875022617192, "ce": 5.6254801750183105, "genuineness": 3.8671910762786865, "identity": 0.5051805973052979, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8605999df9330ed0ef25bddf50cfbf996a9865f2eb16cd3c3712d9e1737f9a18.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "86568d734fa83901a7c53c9b0184996ff96fd979ccaabdca959e5669d3c139dc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ad62d144f5aa0c652718c9c56dd084dd5d5924f2f90ba684246d17dbb2b9f5b2", "generation_seconds_batch": 16.86777987203095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014590814709663391, "target_z": -0.5312500150781282, "ce": 6.427689552307129, "genuineness": 4.344170093536377, "identity": 0.5343894958496094, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/86568d734fa83901a7c53c9b0184996ff96fd979ccaabdca959e5669d3c139dc.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": "86a251e319e5e7efd603351a831ad3a7f2784b7b455aa41d678ead2fab6a3f17", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Someone moved the little blue chair.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5001988662813ee5b2111e077237b88952bd0e9e9d64a862c5367b97c2c9fcb7", "generation_seconds_batch": 19.81471096596215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12727902829647064, "target_z": -0.20312499461495423, "ce": 6.3641486167907715, "genuineness": 4.306513786315918, "identity": 0.20095643401145935, "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_Sourness/86a251e319e5e7efd603351a831ad3a7f2784b7b455aa41d678ead2fab6a3f17.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "872fadfb3b94f208b190d74a11595ef8d55a39acf9e70417fc783825522e7719", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6d1ab5c8652dd4cf59799efb07ca1e2903d2e8f8da2c1847e57ee8f4aff0dd20", "generation_seconds_batch": 22.554490334005095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45324185490608215, "target_z": 0.5507812400376654, "ce": 6.046441555023193, "genuineness": 4.394378662109375, "identity": 0.30233410000801086, "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_Sourness/872fadfb3b94f208b190d74a11595ef8d55a39acf9e70417fc783825522e7719.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "877b4e134cf0da164ea504dc1e0c19dbcbf012c6b3a1e141bbb08b2febc260df", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ddd904b3557cab5024233f22b07e527502a8a5d71f5a254d9353d77d332f7256", "generation_seconds_batch": 27.195999452029355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.59848952293396, "target_z": 0.8867186953417855, "ce": 6.213237762451172, "genuineness": 4.306513786315918, "identity": 0.6816034317016602, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/877b4e134cf0da164ea504dc1e0c19dbcbf012c6b3a1e141bbb08b2febc260df.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "878645938b1897122fd1b63e71ebd6d7c7dae55324f0e9d6848e4d0644e6706e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "89e38372cf60eec31e602f6b240e0cb2d43b0544e4cd081f6eac0345911d8fab", "generation_seconds_batch": 27.42959595506545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07830014824867249, "target_z": -0.31640626480887585, "ce": 6.141753673553467, "genuineness": 4.287685871124268, "identity": 0.6748008131980896, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/878645938b1897122fd1b63e71ebd6d7c7dae55324f0e9d6848e4d0644e6706e.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "87cda48e5db78031c0a28f256facd1a14b2de16b9840b89586bc82fe7b325329", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4c2222b4dcd2d3817b698a29b600fbd339b8a21a6073f9ed49f7d6c9425c66f9", "generation_seconds_batch": 18.290851555066183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.029791146516799927, "target_z": -0.5664062475767294, "ce": 6.2767791748046875, "genuineness": 4.080576419830322, "identity": 0.4193236231803894, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/87cda48e5db78031c0a28f256facd1a14b2de16b9840b89586bc82fe7b325329.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "88683f81ed300e7476436faa4fc0a3b7f3a834025bb5be560c366a963b2fd4f2", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "10fd58cbea4ae1827165824af096717996f668c2fc289b0714278a91c2d907e7", "generation_seconds_batch": 15.678792178980075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48195362091064453, "target_z": 0.6171875220786877, "ce": 6.157639026641846, "genuineness": 4.168440818786621, "identity": 0.5123134851455688, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/88683f81ed300e7476436faa4fc0a3b7f3a834025bb5be560c366a963b2fd4f2.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": "890e7aa71f8ea524b79ffca0f3d08f1526df308e0f8b1db1c4387c2aca7cf437", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The keys are on the kitchen table.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e66bf4f784a690f5f1905300387731a3a6bcc09a80c5953d6f9b727d51676c70", "generation_seconds_batch": 19.099727941094898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06394428014755249, "target_z": -0.3496093713650941, "ce": 6.3641486167907715, "genuineness": 4.319066047668457, "identity": 0.3571268916130066, "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_Sourness/890e7aa71f8ea524b79ffca0f3d08f1526df308e0f8b1db1c4387c2aca7cf437.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "891e70474d9298f19e0bd22400f8c085dc5677a10a0c827cb5bcd2d21015f626", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "523d7f34342510e06c8c4b0b40c5b5d25561a447fd45ff912148aff028169181", "generation_seconds_batch": 25.191174373961985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08674478530883789, "target_z": -0.29687500538504574, "ce": 6.046441555023193, "genuineness": 3.7667744159698486, "identity": 0.24711519479751587, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/891e70474d9298f19e0bd22400f8c085dc5677a10a0c827cb5bcd2d21015f626.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": "895017667a22403be70b367bb149481cc83d1584d128196610513fbe47445a63", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61f22a7ab2a2d8d13d11caa476d46c9c9b745194325ddac440f69779c5a37426", "generation_seconds_batch": 14.503948878962547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1306568682193756, "target_z": -0.1953125253097151, "ce": 6.308549880981445, "genuineness": 4.482243061065674, "identity": 0.6475026607513428, "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_Sourness/895017667a22403be70b367bb149481cc83d1584d128196610513fbe47445a63.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "89830144812d8d7b6224dbf99164e56a276b26e24e2f2ac048a498cb30918642", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cba6706428ba8ce9e30ea52369f50f23d54470be9310a0ecf290a81cb76e0088", "generation_seconds_batch": 21.975240239989944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010743096470832825, "target_z": -0.4726562368066379, "ce": 6.141753673553467, "genuineness": 4.457139015197754, "identity": 0.49933040142059326, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/89830144812d8d7b6224dbf99164e56a276b26e24e2f2ac048a498cb30918642.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": "8acddf35b4f9424e6179c5b25e0676beb6f73dd371bb7470f1bb50e74740dbcb", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "059bdea938c0e8890d8b418f5282cf52c0f7dbaf9a52aa48efcf7d41aaac3cfe", "generation_seconds_batch": 16.60646884702146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08674478530883789, "target_z": -0.29687500538504574, "ce": 6.221180438995361, "genuineness": 4.105680465698242, "identity": 0.761802077293396, "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_Sourness/8acddf35b4f9424e6179c5b25e0676beb6f73dd371bb7470f1bb50e74740dbcb.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "8ae425fb226cb57e12e15d3e389a21a3720fa4a75d34f68453fbe59b3ffa93d6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "956c386fd1455fd91c973d586ada26eac6bf94a09991fb5c6148e4c239c86c55", "generation_seconds_batch": 24.739379816921428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08167800307273865, "target_z": -0.30859376103934383, "ce": 5.9431867599487305, "genuineness": 3.5941832065582275, "identity": 0.4069163203239441, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8ae425fb226cb57e12e15d3e389a21a3720fa4a75d34f68453fbe59b3ffa93d6.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "8b48bece50c805d55ccb37a3a0e579befae6bca1b60dc83964fafcd64170a313", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ce7ae7181be6e07fc889a325760cc89c6a3574458464ac5a3015c8aa63638c36", "generation_seconds_batch": 24.331450346042402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05972196161746979, "target_z": -0.35937500107700915, "ce": 6.006728172302246, "genuineness": 4.243753433227539, "identity": 0.2879101037979126, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8b48bece50c805d55ccb37a3a0e579befae6bca1b60dc83964fafcd64170a313.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "8b8ed0db276c38a5ff65f2087054fedcc797037d4299d8ecaf51b99c129e4344", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bb919ecfdbde31134c32af2fe7a43a0f06b28a793a0b5413df73e5c6e5bfd619", "generation_seconds_batch": 16.85071189503651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.024724364280700684, "target_z": -0.5546874919224314, "ce": 6.086154937744141, "genuineness": 4.582659721374512, "identity": 0.5983929634094238, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8b8ed0db276c38a5ff65f2087054fedcc797037d4299d8ecaf51b99c129e4344.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "8bacd6d021f467d4a5f325520884b79b482e9f8043bf59eb249b84a39a5d7f9b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c9ac7de73e2d1735fd8a76cf6239d97361bc075536eeff8ad9780d157640f367", "generation_seconds_batch": 17.213262684061192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10616744309663773, "target_z": -0.251953125942383, "ce": 5.8875885009765625, "genuineness": 4.369274139404297, "identity": 0.7394208908081055, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8bacd6d021f467d4a5f325520884b79b482e9f8043bf59eb249b84a39a5d7f9b.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "8d5deb78ac67a752e68bd81ec9c7910c989a8a39e72ec5df588c8aaf76c8a8e6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4bdd5f178497593dd010657b302fa4b8ec21dbcccb5c2bcf75aa7cb9dca79561", "generation_seconds_batch": 25.14194026601035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04114377498626709, "target_z": -0.40234373734514245, "ce": 6.2767791748046875, "genuineness": 4.362998008728027, "identity": 0.3479609191417694, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8d5deb78ac67a752e68bd81ec9c7910c989a8a39e72ec5df588c8aaf76c8a8e6.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "8d7e599efeb7b749644543228ff624d4667b9e5beaf8648d3380f2262c6b4d61", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29cb225af6199e5f57d1e5bc7e59f0923a8bc29c2aad570d48189f4057bf0712", "generation_seconds_batch": 22.163581931963563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06816659867763519, "target_z": -0.33984374165317904, "ce": 5.879645347595215, "genuineness": 3.7667744159698486, "identity": 0.23180744051933289, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8d7e599efeb7b749644543228ff624d4667b9e5beaf8648d3380f2262c6b4d61.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "8df104a9bf7ce41045a81f32188531eb3b8de5e63bbd9650f89c24f4013d8238", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ed359ef900c8717709a6dede396f88e5476649992b1ce1c8c5a19d578a1a06c", "generation_seconds_batch": 22.975997025030665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6035563349723816, "target_z": 0.8984375199246694, "ce": 6.229123115539551, "genuineness": 3.9048471450805664, "identity": 0.42649757862091064, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8df104a9bf7ce41045a81f32188531eb3b8de5e63bbd9650f89c24f4013d8238.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "8efa8873f058ca5642204a2c180e8855015446eaaec964e6c361b6114627fb7c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b3e122e3355c4e69a48a40f30cbd1c240ef966541f4669d31388ba5338964c85", "generation_seconds_batch": 25.787841791054234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1036340519785881, "target_z": -0.257812503769532, "ce": 6.173524379730225, "genuineness": 4.18099308013916, "identity": 0.4529980421066284, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8efa8873f058ca5642204a2c180e8855015446eaaec964e6c361b6114627fb7c.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "8f213beba0d5f3caaef41b04251cd484b41344d48b31459c0febc0500302d1bf", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "35bbab8d6b4225b9552ee40687773cd35746c7dc38f82b9bdae92671e802f698", "generation_seconds_batch": 22.39377275807783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06309981644153595, "target_z": -0.35156249730747713, "ce": 6.125868320465088, "genuineness": 4.099404335021973, "identity": 0.37926656007766724, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8f213beba0d5f3caaef41b04251cd484b41344d48b31459c0febc0500302d1bf.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": "8f2953e6be10bc639e188f5def5767de57997cf85f5f9a8867d7ab6f265f1e64", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8235e02588a41f45b8171d1bdd105bddac809f102eb117ae4df320a4e4eb5845", "generation_seconds_batch": 24.048293755971827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08167800307273865, "target_z": -0.30859376103934383, "ce": 6.268836498260498, "genuineness": 4.319066047668457, "identity": 0.7323596477508545, "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_Sourness/8f2953e6be10bc639e188f5def5767de57997cf85f5f9a8867d7ab6f265f1e64.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "8f65c95758c1136ed80bb43d23e3f16f1303715bf397cb198263630799ab0675", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4d2baafd93cf81739e80e8d9111077fb7d8dd9a0ad8d6ae6f924aff9475aa382", "generation_seconds_batch": 23.852399950963445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06141088902950287, "target_z": -0.35546874919224314, "ce": 6.1020402908325195, "genuineness": 4.607763767242432, "identity": 0.644891619682312, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8f65c95758c1136ed80bb43d23e3f16f1303715bf397cb198263630799ab0675.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "8f80bfd5f5a2652692e4586a1845557167a8be97c4cb981aadb3e8960f9f8544", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f6252cbea51f7177a311779e367d76ea51935038180f8bafb149bb0ee9eda5b1", "generation_seconds_batch": 23.83247783803381, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6204456090927124, "target_z": 0.9375000387723295, "ce": 5.728734970092773, "genuineness": 3.8169827461242676, "identity": 0.6422997713088989, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8f80bfd5f5a2652692e4586a1845557167a8be97c4cb981aadb3e8960f9f8544.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": "8fd18b6b4b36250327a76aad6d307ac07664b4bc049d17cf16053613d105cada", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Someone moved the little blue chair.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fa8f52f58f33e42b99d29176f825042937c0aa6ea1575a64e12d864ee7a8928", "generation_seconds_batch": 23.880886728991754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11207868903875351, "target_z": -0.23828124434570194, "ce": 6.332377910614014, "genuineness": 4.042920112609863, "identity": 0.3195250332355499, "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_Sourness/8fd18b6b4b36250327a76aad6d307ac07664b4bc049d17cf16053613d105cada.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "8ffc79c9e6365d7f66bab26d9cab4c6a2245b3b0d5a3efc99a27c0008f840260", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ee94deb3b137283913b5e90b8fc88e8fa7d9922971ee2035aa834ed5689890ec", "generation_seconds_batch": 26.015927143977024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015809863805770874, "target_z": -0.4609375156166327, "ce": 6.09409761428833, "genuineness": 4.20609712600708, "identity": 0.6272366046905518, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/8ffc79c9e6365d7f66bab26d9cab4c6a2245b3b0d5a3efc99a27c0008f840260.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "901d79291edeb95d05d56974d2009f0655da01bdb4efe3fa5d0f9cd878f59f21", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4e84d47fa02030434af3d9f8da66f23d9e13d0bd9b821ef5e66f7fb340d23f98", "generation_seconds_batch": 21.421070821001194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032699137926101685, "target_z": -0.42187499676897255, "ce": 5.847874641418457, "genuineness": 3.9425034523010254, "identity": 0.34749796986579895, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/901d79291edeb95d05d56974d2009f0655da01bdb4efe3fa5d0f9cd878f59f21.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "9078e7a7e5686e9cc5829f12c068322e9bc90da8471695cec7af918b15635e28", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "89ce7a9e2a6502bde6407bee4c99e0968a5abef4124b4a021da4f26c67cc3c93", "generation_seconds_batch": 23.00159340305254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06647767126560211, "target_z": -0.3437499935379451, "ce": 6.268836498260498, "genuineness": 3.9676074981689453, "identity": 0.1647270917892456, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9078e7a7e5686e9cc5829f12c068322e9bc90da8471695cec7af918b15635e28.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "90c7b7ecd00213d1c5d90494f07f81d764aad4a35440d6caaa5b1db74d67da34", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "581113937ed6b6e1051e73399982f803d62ecc756a3659a275e9330d2f68229a", "generation_seconds_batch": 24.320228012045845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06309981644153595, "target_z": -0.35156249730747713, "ce": 6.149696350097656, "genuineness": 4.18726921081543, "identity": 0.48044347763061523, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/90c7b7ecd00213d1c5d90494f07f81d764aad4a35440d6caaa5b1db74d67da34.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "9122443ddad30cd7ddc8faa1730afbee6bb9072230ec3a3731a9086e537b4bbd", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fd49bb6acd38c5fde4b9593df131d397f1d1eac5562ed2ce4bdd8f955a3058d1", "generation_seconds_batch": 16.478162411018275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02594342827796936, "target_z": -0.4375000043080366, "ce": 6.213237762451172, "genuineness": 4.3127899169921875, "identity": 0.3420317769050598, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9122443ddad30cd7ddc8faa1730afbee6bb9072230ec3a3731a9086e537b4bbd.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "9154f24f55d8959d5cf23d1ca66b3590b0c8cfeb0fa2602dd4e4a2319b296f64", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8247d5a8f840425ada7b99cf8e86e259d76b00b6418ce7b2712d41509676a42d", "generation_seconds_batch": 26.291464239009656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.244659423828125, "target_z": 0.06835937351911242, "ce": 6.086154937744141, "genuineness": 4.118232727050781, "identity": 0.27902233600616455, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9154f24f55d8959d5cf23d1ca66b3590b0c8cfeb0fa2602dd4e4a2319b296f64.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "9161e6d77a708432928532d1941596a94e2b29e3725ebbcf3a2a247c20880c67", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fff7331dd89e12be36bdbbe0f1fd8cbe7b84ad129919851059db42013a48efed", "generation_seconds_batch": 20.340080408961512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18132467567920685, "target_z": -0.07812500323102746, "ce": 6.1894097328186035, "genuineness": 4.168440818786621, "identity": 0.5206338167190552, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9161e6d77a708432928532d1941596a94e2b29e3725ebbcf3a2a247c20880c67.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "92436b8bd1f42e57ee6eb380d0508f41afe877d5bb8a3c4cda5e148a89486ec6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8341463381ac4817baf6bd8924ddcec3fe95e3b5e12555d129ae3af1f603bf41", "generation_seconds_batch": 23.414696492953226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11292315274477005, "target_z": -0.23632811840331894, "ce": 6.229123115539551, "genuineness": 4.557555198669434, "identity": 0.526123046875, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/92436b8bd1f42e57ee6eb380d0508f41afe877d5bb8a3c4cda5e148a89486ec6.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "92ebe5cea11b3605e56e23afd9636d86bd65518ec3a78ee60dae1a41dd34fa53", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0fa610639f49b6e0e59aa1b5fba98bf1f81236672f34a95ef1f0b263a3436034", "generation_seconds_batch": 21.537630146951415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3333280682563782, "target_z": 0.2734374940764497, "ce": 5.4388275146484375, "genuineness": 3.562803030014038, "identity": 0.30205509066581726, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/92ebe5cea11b3605e56e23afd9636d86bd65518ec3a78ee60dae1a41dd34fa53.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "92f9a3d5f733b1c7f7a9b977ffc5cbac43040e1164e9456d08531e754a1991d5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5df8741ccbe75de2e77027bd8918220a9ece04f5fdf38b4b72377e9c04cada3e", "generation_seconds_batch": 23.748547647963278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 5.998785495758057, "genuineness": 4.494794845581055, "identity": 0.736431360244751, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/92f9a3d5f733b1c7f7a9b977ffc5cbac43040e1164e9456d08531e754a1991d5.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "935a154b3d60bb0b52c65dc511b57f956e63cca682aebd51ec105b3e6a744d31", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "68abc8b2326255348fd0287e9a85b79d25d2bb01996197a446f124414da8a101", "generation_seconds_batch": 22.15783742093481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 5.95112943649292, "genuineness": 4.080576419830322, "identity": 0.5912367105484009, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/935a154b3d60bb0b52c65dc511b57f956e63cca682aebd51ec105b3e6a744d31.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "935a5d2eda767f87da2345e7827564012f85faca90f4d0a763f9461722cd0d5d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d84a125a2c705c33eaf4a25ce592da2e51a87a4bf7ddeb4ccff08f7a9f8fd4a8", "generation_seconds_batch": 15.853461542981677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01796865463256836, "target_z": -0.5390624843833672, "ce": 6.23706579208374, "genuineness": 4.011539936065674, "identity": 0.4911777377128601, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/935a5d2eda767f87da2345e7827564012f85faca90f4d0a763f9461722cd0d5d.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "93643cf6cf12c5543528611483b7be4943a772e0f3b7019da3898d2115b2d5b1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f916a046a41d81de8024605f91cac15d9b7d18f934c99370ec89dfd34d1a7da2", "generation_seconds_batch": 16.563104749075137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053810715675354004, "target_z": -0.37304688267369024, "ce": 5.903473377227783, "genuineness": 4.425758361816406, "identity": 0.5181131958961487, "hypothesis": "J'ai trouvé la 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_Sourness/93643cf6cf12c5543528611483b7be4943a772e0f3b7019da3898d2115b2d5b1.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "947085272920af4bc2377efee511d67df7f8e110426574b188da7513276a99cc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "420b4d60633701f4bbc99bb7d55f0d86d28db012a0e7d6688d90abe80f1e730f", "generation_seconds_batch": 23.775772585067898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01965758204460144, "target_z": -0.5429687362681334, "ce": 6.205295085906982, "genuineness": 4.65797233581543, "identity": 0.7413848042488098, "hypothesis": "J'ai trouvé la 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_Sourness/947085272920af4bc2377efee511d67df7f8e110426574b188da7513276a99cc.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "94a0a7dc706d73cf7125d8d2f96bcf3248e8624ff73c939f7de4785c425d4360", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cad31b5ec73654b596d5ebbb827ed406eb29048b330b18f1cff8bd85d29c1e2d", "generation_seconds_batch": 24.143614604021423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 6.141753673553467, "genuineness": 3.8922953605651855, "identity": 0.2722814381122589, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/94a0a7dc706d73cf7125d8d2f96bcf3248e8624ff73c939f7de4785c425d4360.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "94dd891652024df8a190c8e3ec23fa12375b9b7b39ad143f3142a94373697f66", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e28b4c4e6a760847f0b5993284361065927e945d0721d68571c123d5a198a95d", "generation_seconds_batch": 25.14194026601035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02134650945663452, "target_z": -0.5468749881528994, "ce": 6.260893821716309, "genuineness": 4.344170093536377, "identity": 0.5072448253631592, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/94dd891652024df8a190c8e3ec23fa12375b9b7b39ad143f3142a94373697f66.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "94eb6310753dc9a756d26d2129bc5f085956b348720b16d37f13a13791ebd6e3", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f0077b8950533dc9024fdbd287430df1e58a2a10ce0bc1fddbdaa0d422562fd0", "generation_seconds_batch": 22.41437520692125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009898632764816284, "target_z": -0.4746093627490209, "ce": 6.086154937744141, "genuineness": 4.231201171875, "identity": 0.5635061860084534, "hypothesis": "J'ai trouvé la 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_Sourness/94eb6310753dc9a756d26d2129bc5f085956b348720b16d37f13a13791ebd6e3.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": "95250a8007529d6769f01b90f3f7cdca4e531d91e34c32316e1f45bafa73a762", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da9c70e4982fc5ba942267ab80afc3fb97061de30c7b5250afe983c1d2967ee5", "generation_seconds_batch": 23.93971678800881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029321283102035522, "target_z": -0.4296875005385046, "ce": 6.173524379730225, "genuineness": 4.168440818786621, "identity": 0.6364914178848267, "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_Sourness/95250a8007529d6769f01b90f3f7cdca4e531d91e34c32316e1f45bafa73a762.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "9529c4dad52942bad753fba9710fc260a4820139b68249c602698a5bb78106b8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6e55285321f3ed738517adbb1af6902c41ccf6889f5cfec6cb968c984030196b", "generation_seconds_batch": 19.926758044981398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49884286522865295, "target_z": 0.656249971997762, "ce": 5.831989288330078, "genuineness": 3.478076457977295, "identity": 0.395658016204834, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9529c4dad52942bad753fba9710fc260a4820139b68249c602698a5bb78106b8.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "958b2fbfb2591c37d11a7edfe4b950a79719870135321147ae2cf6c0b8fdabcc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0500f3806e4e9bfcb60b1ac83b5b30d76a51b3fa931c98ad735ccb9316bd1d33", "generation_seconds_batch": 24.45451825996861, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.214792251586914, "target_z": 4.624999887991048, "ce": 5.935244083404541, "genuineness": 3.5439748764038086, "identity": 0.5907813906669617, "hypothesis": "De deur 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_Sourness/958b2fbfb2591c37d11a7edfe4b950a79719870135321147ae2cf6c0b8fdabcc.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "95bd02b43707dcd239a101f4dfe26a7f91fba0ecec4b71d7cb7c3909a90134cd", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d20b3b03f35512664f0bc7c1d7e4b8c0ad3b5dd02d654026773345267b9c8127", "generation_seconds_batch": 23.803256203071214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10278958827257156, "target_z": -0.259765629711915, "ce": 6.252951145172119, "genuineness": 4.595211505889893, "identity": 0.4801012873649597, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/95bd02b43707dcd239a101f4dfe26a7f91fba0ecec4b71d7cb7c3909a90134cd.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "95d5f784e43d074daeb642a3520284d11de5e67f7983eeb2492c9c24415aec2d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bd7e0363747d3976de685495e5546760efbf012eb1a28b92003e8f71e2f4faa9", "generation_seconds_batch": 18.35764309798833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11883439123630524, "target_z": -0.22265625403878433, "ce": 6.213237762451172, "genuineness": 4.381826400756836, "identity": 0.5620384216308594, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/95d5f784e43d074daeb642a3520284d11de5e67f7983eeb2492c9c24415aec2d.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": "967a1ffcd585b1922cb539b6785eb6a2745189b4439fdc4cab8f0f0847f03709", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a5575a237eaf8ddbae59914e035921d473c5b99c67f57d48b715eca2e3431eb", "generation_seconds_batch": 24.029214910930023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44479721784591675, "target_z": 0.5312499806138352, "ce": 6.332377910614014, "genuineness": 4.2374773025512695, "identity": 0.48899269104003906, "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_Sourness/967a1ffcd585b1922cb539b6785eb6a2745189b4439fdc4cab8f0f0847f03709.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "967ff6f63de87451ba5d89f588222f003b395ef6e231359b03efe55287170e7a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0c4918510aa571fdc40d82ebdc0f82408f62c2153cf4533a726a50f9dc5fe003", "generation_seconds_batch": 24.548798877047375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39919620752334595, "target_z": 0.42578124865373856, "ce": 6.038498878479004, "genuineness": 4.149612903594971, "identity": 0.39640381932258606, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/967ff6f63de87451ba5d89f588222f003b395ef6e231359b03efe55287170e7a.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": "968e40ff38a32a9dfdf13d2efd8bb04bddaf9310fdd5f626b64dffda471d9fbe", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "19c5f31e91cd7b0d32eff30a8b428d6985b5508116f7171c6cb7947a038a23eb", "generation_seconds_batch": 22.65714738308452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12052331864833832, "target_z": -0.2187500021540183, "ce": 6.070269584655762, "genuineness": 4.18099308013916, "identity": 0.6534546613693237, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/968e40ff38a32a9dfdf13d2efd8bb04bddaf9310fdd5f626b64dffda471d9fbe.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "96a1cbd05eac8214543a2462f38a2384b67a97ea75bee6f28580dd35d9deae67", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1899961cdbe41492bb3092bc6470bec738af1f17b4a1230a830165a74ec6ac53", "generation_seconds_batch": 25.191174373961985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16274648904800415, "target_z": -0.12109373949916076, "ce": 6.109982967376709, "genuineness": 4.005263805389404, "identity": 0.4115670323371887, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/96a1cbd05eac8214543a2462f38a2384b67a97ea75bee6f28580dd35d9deae67.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "96dbaeff3af8285e619f2f7f6bce75324614dbb6153fa5f79c147b73d17c5d86", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bb79747a1c5b177ed2879acb896095ef77b15be6079fdad9f8e4daef370d3cc4", "generation_seconds_batch": 17.738243576022796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6471574306488037, "target_z": 5.624999819062462, "ce": 5.411027908325195, "genuineness": 3.6192874908447266, "identity": 0.22553642094135284, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/96dbaeff3af8285e619f2f7f6bce75324614dbb6153fa5f79c147b73d17c5d86.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "9740da397c97a813f9e4a1942ecd54462ba038b718d5651fcd3dff5269b4ee0c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4ae562dc13816f749d57dead5d28801222506f7bebd1c943fe5c47d39473018b", "generation_seconds_batch": 25.131208483944647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19314716756343842, "target_z": -0.050781240037665334, "ce": 6.149696350097656, "genuineness": 4.369274139404297, "identity": 0.6973338723182678, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9740da397c97a813f9e4a1942ecd54462ba038b718d5651fcd3dff5269b4ee0c.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "976582bf44e02ada6b85e64a87dc02e6536b35c91be1ce4b40b0e7b2f86cc419", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "20142c2b0619eea16bc286900e0b72043074c4771a5f94c65359e4f7912f7d80", "generation_seconds_batch": 24.28647373407148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03148007392883301, "target_z": -0.5703124994614954, "ce": 6.260893821716309, "genuineness": 4.457139015197754, "identity": 0.4416547417640686, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/976582bf44e02ada6b85e64a87dc02e6536b35c91be1ce4b40b0e7b2f86cc419.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "976626e5cc90d79f94c6ada52bf49bec12ae61f6cb1c4c20ed3e88cdd0ae78fe", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8f9c570eb7c7c2c5b9703fdf1ecd5d4cc29c2b2547b9934dededfa251f1cf91", "generation_seconds_batch": 17.757058470975608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0056763142347335815, "target_z": -0.4843749924609359, "ce": 6.3641486167907715, "genuineness": 4.262581825256348, "identity": 0.34046900272369385, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/976626e5cc90d79f94c6ada52bf49bec12ae61f6cb1c4c20ed3e88cdd0ae78fe.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "977425e896bb5b26feb1030b0222bdcc536e62344c554a871bd636cad330856a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5cd3d35f95664d64de18303c0fee126dfe6b908500e056527c7f4ab08ded5e50", "generation_seconds_batch": 25.18252452800516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.4515180587768555, "genuineness": 4.13078498840332, "identity": 0.4214552938938141, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/977425e896bb5b26feb1030b0222bdcc536e62344c554a871bd636cad330856a.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "97aa21ca3592c704b5b1a4c0c734666e53696cb4f65efd378fbc5ab60bf3e810", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "229a27f91359ee7b83f1cdf9083d415efca64b3a6d5a07b5852fdc1564a499a7", "generation_seconds_batch": 23.999825958977453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03823578357696533, "target_z": -0.5859375070005595, "ce": 6.149696350097656, "genuineness": 4.356721878051758, "identity": 0.6480330228805542, "hypothesis": "J'ai trouvé la 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_Sourness/97aa21ca3592c704b5b1a4c0c734666e53696cb4f65efd378fbc5ab60bf3e810.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "99267006ab95e10b27bec80ba758e2e53a7afc53945d8764b742d0a7c0ddaeba", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4b68dd1b8917d92b70fa26e437f71c66b9b4263a4212c38cd2f6d1ba484fcde6", "generation_seconds_batch": 16.165709855034947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02763235569000244, "target_z": -0.4335937524232706, "ce": 6.022613525390625, "genuineness": 4.105680465698242, "identity": 0.48469167947769165, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/99267006ab95e10b27bec80ba758e2e53a7afc53945d8764b742d0a7c0ddaeba.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "e6427af5b8c54f6ec160aab450198244f4701298feede449d1597bb949afc946", "generation_seconds_batch": 18.595297037041746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07407784461975098, "target_z": -0.326171860056498, "ce": 6.41180419921875, "genuineness": 4.632867813110352, "identity": 0.604363203048706, "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_Sourness/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "9a549997d5c08f29657264ee5376b4594f941bbfc11a05c6191daf93e662b495", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8085bd0c710f24fccf272f746307dffdeac6bbecf41eb5cd799773763a78a1a0", "generation_seconds_batch": 16.666050552972592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018343254923820496, "target_z": -0.4550781377894837, "ce": 6.332377910614014, "genuineness": 4.469690799713135, "identity": 0.4285773038864136, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9a549997d5c08f29657264ee5376b4594f941bbfc11a05c6191daf93e662b495.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "9a631405081698eb6f46e6e189192b49de0ed9034ed0186db99281f13a909f66", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ee7224df5db4b9462eacf31a4054f9e9e6ff06e848e40fdc288500d5cec1188e", "generation_seconds_batch": 24.028510999050923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40510743856430054, "target_z": 0.43945309578612674, "ce": 5.637393951416016, "genuineness": 3.8922953605651855, "identity": 0.44636082649230957, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9a631405081698eb6f46e6e189192b49de0ed9034ed0186db99281f13a909f66.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "9a8207074911a2137a3aa9566d7d49633badd7f4caff71bd4a90096acf8cf5b8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bee75e9e67de7c7cd38ce8793c04d678c2f6e6b503d2149a52296e6088709b02", "generation_seconds_batch": 27.802313773077913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9445641040802002, "target_z": 4.000000137857172, "ce": 6.0305562019348145, "genuineness": 3.7416701316833496, "identity": 0.6217653155326843, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9a8207074911a2137a3aa9566d7d49633badd7f4caff71bd4a90096acf8cf5b8.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": "9ae2b00e7a8a831b759f9d5c1530b2467b86a986bb53c5dec3034146bb3c345b", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6caece329bccf1f25d17ff50d57b3946865c47437fe614edf33dd0a04419d569", "generation_seconds_batch": 14.482412993093021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2134142816066742, "target_z": -0.003906251884766018, "ce": 6.109982967376709, "genuineness": 3.9550557136535645, "identity": 0.5913790464401245, "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_Sourness/9ae2b00e7a8a831b759f9d5c1530b2467b86a986bb53c5dec3034146bb3c345b.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "9b09b053107f8abc35a74c774f8dccb43dc7e5f5e290895db845ed018146a139", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "443864e011144a34c0dda2190c24c36f3bf0abeb9cfbbd8d0a09ebf276981d46", "generation_seconds_batch": 24.609106983989477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18301360309123993, "target_z": -0.07421875134626144, "ce": 6.086154937744141, "genuineness": 4.2751336097717285, "identity": 0.7176786661148071, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9b09b053107f8abc35a74c774f8dccb43dc7e5f5e290895db845ed018146a139.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "9b2f9a5d9b6bdb22c7c743dfc72c7a3236e427e140f284971ee3e0b4fc5c42b6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "93fb944fb56eb5a344a6db6e8d30b3ec97ecb33e544fa22b023cff10c03515c5", "generation_seconds_batch": 17.817381756030954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.034388065338134766, "target_z": -0.41796874488420654, "ce": 6.252951145172119, "genuineness": 4.369274139404297, "identity": 0.3713229298591614, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9b2f9a5d9b6bdb22c7c743dfc72c7a3236e427e140f284971ee3e0b4fc5c42b6.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "9bb65ba7bb5ad12b934bf0f66d9d06779b5d25165e82e8097c213471f9b38ed1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b140dc3dff2b84ed7d1e4d45c24fe70cf7099816a42c6948df417aeb8222d7b5", "generation_seconds_batch": 17.218748182058334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06647767126560211, "target_z": -0.3437499935379451, "ce": 6.0305562019348145, "genuineness": 4.124508857727051, "identity": 0.6196721792221069, "hypothesis": "Ik 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_Sourness/9bb65ba7bb5ad12b934bf0f66d9d06779b5d25165e82e8097c213471f9b38ed1.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "9c01c91c37e4d5f481017874796eecdcc055bb5d063bf971c17698235767a61f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b14d54f31151a8b68d66e98043f5e4b984503204d1058f73fe10715384016333", "generation_seconds_batch": 23.344303463003598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0766112208366394, "target_z": -0.32031251669364186, "ce": 6.062326908111572, "genuineness": 4.256305694580078, "identity": 0.5988091230392456, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9c01c91c37e4d5f481017874796eecdcc055bb5d063bf971c17698235767a61f.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "4ed13ef9e67e32aad4d3a36b0363b13dd52546fc4849fd62dbbca9cf8b6bf83a", "generation_seconds_batch": 16.319907204946503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0951894223690033, "target_z": -0.2773437459612157, "ce": 6.284721851348877, "genuineness": 4.519899368286133, "identity": 0.6836748123168945, "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_Sourness/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "13e6fc1f50169a5857a3ec8b0ed0a0b03364e27ca6d106104ded5b39a7d685aa", "generation_seconds_batch": 18.526117490953766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14839060604572296, "target_z": -0.15429688051967191, "ce": 5.919358730316162, "genuineness": 4.545003414154053, "identity": 0.7395060062408447, "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_Sourness/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.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": "9ca8dd9ea6022fd8082439d4ba6d01b8ea2c94077f594f294592d15bfaaf0e17", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Escribí el número en el sobre.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "698f84bf05e53c8b613995cf072fe175246231242b0d3639f2331c6162689e78", "generation_seconds_batch": 22.45560171699617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08505585789680481, "target_z": -0.3007812572698118, "ce": 6.205295085906982, "genuineness": 4.2751336097717285, "identity": 0.6113725900650024, "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_Sourness/9ca8dd9ea6022fd8082439d4ba6d01b8ea2c94077f594f294592d15bfaaf0e17.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "9cff4809512c366248a605a67413773a88c299ba9fc433efbaf1ae28f287c29d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd4c6b39f7c5815bb228a861683a8cf4e6c724c2649f8cd1afd6dee950efe80e", "generation_seconds_batch": 20.01468350889627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.691380500793457, "target_z": 1.1015624800753308, "ce": 5.426913261413574, "genuineness": 3.8044304847717285, "identity": 0.5606895685195923, "hypothesis": "Si j'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9cff4809512c366248a605a67413773a88c299ba9fc433efbaf1ae28f287c29d.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "9e0579ed17dddbc762a82906d9e4f4de5647b65c30fc6597d42d55b604520810", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "dcd00fd63cfa75daf8c7b85230fb80b9b4c0941a0adbb71314fab8f5d0f27b5c", "generation_seconds_batch": 21.440842052921653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11292315274477005, "target_z": -0.23632811840331894, "ce": 6.205295085906982, "genuineness": 4.444586753845215, "identity": 0.3607064485549927, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9e0579ed17dddbc762a82906d9e4f4de5647b65c30fc6597d42d55b604520810.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "9e0fb9fbbb8fab5d8436212ee4b847f8195dd06b2ad1b8d3065a9ee644ffa05e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "84908b5da9b49cd38840af516cd36a7fd9a0e4677dd9c985cd424c1a5d684b58", "generation_seconds_batch": 23.794633826008067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019187718629837036, "target_z": -0.4531250118471007, "ce": 6.133810997009277, "genuineness": 4.369274139404297, "identity": 0.6014873385429382, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9e0fb9fbbb8fab5d8436212ee4b847f8195dd06b2ad1b8d3065a9ee644ffa05e.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "9eefdfc001b6930d071f391426f531f2ca0828c4c121b099dbed9da4c06a62cc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5cdc6ba3e8236cc33fcf3a1e28ce0a5a726b60330c70ed36dd6a7cc32d75abf4", "generation_seconds_batch": 16.551035907003097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21679213643074036, "target_z": 0.003906251884766018, "ce": 5.673136234283447, "genuineness": 3.810706615447998, "identity": 0.33661389350891113, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/9eefdfc001b6930d071f391426f531f2ca0828c4c121b099dbed9da4c06a62cc.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": "9fa5553816c8d44d64b44cbdcc1bb8e12269125b9e01ef4b0ddc9baae6099468", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4a71f9552d16a144773af9c7e3cb76430f67b3c4d5330c17eae360f1d88387b", "generation_seconds_batch": 15.474634955986403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18132467567920685, "target_z": -0.07812500323102746, "ce": 6.1020402908325195, "genuineness": 4.300237655639648, "identity": 0.8545862436294556, "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_Sourness/9fa5553816c8d44d64b44cbdcc1bb8e12269125b9e01ef4b0ddc9baae6099468.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": "9fab6019e0d1921d5cb914522a96270168e4577ec1faf5396b486066a94b8958", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0b134f73a6d97b1443008b61a5755849c53b8e5c8e9fcec128037f1813a56c4", "generation_seconds_batch": 16.44014199101366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05127732455730438, "target_z": -0.37890626050083925, "ce": 6.070269584655762, "genuineness": 4.6203155517578125, "identity": 0.6395136713981628, "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_Sourness/9fab6019e0d1921d5cb914522a96270168e4577ec1faf5396b486066a94b8958.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "a02152c1f2466a3f97a444be9cfa721b671bc4afd5cc07d179ef05fb8d2731e6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "40e55b02aa73d13ea6db91158895e3937b9519756ec83e703804a66c501984e7", "generation_seconds_batch": 21.421070821001194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09012264013290405, "target_z": -0.2890625016155137, "ce": 5.728734970092773, "genuineness": 3.578493118286133, "identity": 0.18435800075531006, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a02152c1f2466a3f97a444be9cfa721b671bc4afd5cc07d179ef05fb8d2731e6.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "a039f00f1666208ae53a393342fcacafcef31f137b062b779458df72b74467e7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04c41a31c83aa6ed288ed1d6aff13cc5e2c20e7da787c94d5c562ea8d93fde7c", "generation_seconds_batch": 16.676183170988224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03776592016220093, "target_z": -0.41015624111467447, "ce": 6.1020402908325195, "genuineness": 3.9676074981689453, "identity": 0.3359677195549011, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a039f00f1666208ae53a393342fcacafcef31f137b062b779458df72b74467e7.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "a0f5d9af99b03ab72ec746b017e18489a534d7487e861db033ba718d05b802d2", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "621468156846bbab07b84f519b51704fc259f05078e9951114884ab5543b6a90", "generation_seconds_batch": 23.35217729001306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16274648904800415, "target_z": -0.12109373949916076, "ce": 5.200547218322754, "genuineness": 4.049196243286133, "identity": 0.6824592351913452, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a0f5d9af99b03ab72ec746b017e18489a534d7487e861db033ba718d05b802d2.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "a12432e647c499193db6269c5199b77215c59f485fba72b460b1983a3dd30191", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a0b0cb31f490fa41d877394729841efd5409de98e8c0f4b2a0f75774939ffc91", "generation_seconds_batch": 23.509999967063777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08843371272087097, "target_z": -0.29296875350027973, "ce": 6.141753673553467, "genuineness": 4.193545341491699, "identity": 0.42775219678878784, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a12432e647c499193db6269c5199b77215c59f485fba72b460b1983a3dd30191.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "a16fa693faea84fdb9cabaf4b798a4b05a86ec67ea1cad7646985bff793a235b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5685dcb4cccbf61ece80f284fcb138d4271a99bc50f98aad10890c4b2f3e63c7", "generation_seconds_batch": 19.36871140799485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24719281494617462, "target_z": 0.07421875134626144, "ce": 5.8875885009765625, "genuineness": 4.193545341491699, "identity": 0.6394479870796204, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a16fa693faea84fdb9cabaf4b798a4b05a86ec67ea1cad7646985bff793a235b.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "a194dea08dac31cabb7af40b95b3a64d2a8c2b660b1bc3cae1c627bda925c1ea", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4bf8a8a27961220ae48b47fcc6d374be051757393208bc566aa03211a93fb7bf", "generation_seconds_batch": 25.260001125978306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02134650945663452, "target_z": -0.5468749881528994, "ce": 6.372091293334961, "genuineness": 4.281409740447998, "identity": 0.4840059280395508, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a194dea08dac31cabb7af40b95b3a64d2a8c2b660b1bc3cae1c627bda925c1ea.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "a1a6ce4979fd8e45f0d50a5d757ce789765403ed0badbd724694406768b093de", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "685882d2e72d48c4e6f173b0c571aa821dbabdfd9d563247983b2a2b067a2c30", "generation_seconds_batch": 24.877978409989737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2007473260164261, "target_z": -0.03320314102051115, "ce": 6.109982967376709, "genuineness": 4.356721878051758, "identity": 0.4321023225784302, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a1a6ce4979fd8e45f0d50a5d757ce789765403ed0badbd724694406768b093de.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "a2a1691d49c7de24df1d4051cfc18fa2967df1cd116451180883c5bc4d86f7ee", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c8e71b4328eadc8f440d579cbaac0f96008a847e9129feb4f633147246eb629f", "generation_seconds_batch": 24.06782561703585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 5.780362129211426, "genuineness": 4.086852550506592, "identity": 0.4782262444496155, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a2a1691d49c7de24df1d4051cfc18fa2967df1cd116451180883c5bc4d86f7ee.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "a2a7057fa3c2492d212afa1171b05c118d2049135ba43c2fcb8a18037f4deed8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5a8d956de542a966e69963045142afd5d1f36c39d3383ecfe117078c01cb3ead", "generation_seconds_batch": 25.389819030067883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08843371272087097, "target_z": -0.29296875350027973, "ce": 6.181467056274414, "genuineness": 3.9425034523010254, "identity": 0.4161026179790497, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a2a7057fa3c2492d212afa1171b05c118d2049135ba43c2fcb8a18037f4deed8.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "a2d37d46a24153b2d1720ec70afbe86753c06747615d9c6e61d6893b87c546dc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "14f47ca187ca7f489c9c0f51e6d98fdb644c6550a1b9e626bebd8047679f257c", "generation_seconds_batch": 17.6255942779826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0994117334485054, "target_z": -0.2675781334814471, "ce": 6.149696350097656, "genuineness": 4.570107460021973, "identity": 0.6854453086853027, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a2d37d46a24153b2d1720ec70afbe86753c06747615d9c6e61d6893b87c546dc.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "a3b347dda7f64b181a90ab49887fcf4771757ece1d958a229110c16f8dd227e4", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8fb3be20eeaeb063fd5274c51117197ae6de0f667cb603a086d326ccfd1845aa", "generation_seconds_batch": 24.139026604010724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13572365045547485, "target_z": -0.18359376965541704, "ce": 6.125868320465088, "genuineness": 4.137060642242432, "identity": 0.5531386137008667, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a3b347dda7f64b181a90ab49887fcf4771757ece1d958a229110c16f8dd227e4.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "a3d26b999049ede09ffbeb14c69e81cab784a8587711c0a343a0709f492c30e5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cacb0bd1fcaf7601960efcf1fbc7393d9071f506def8ff2226030ae762cdeeb4", "generation_seconds_batch": 22.554490334005095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3162834644317627, "target_z": 2.5468752638672423, "ce": 5.863759994506836, "genuineness": 3.8044304847717285, "identity": 0.4671187400817871, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a3d26b999049ede09ffbeb14c69e81cab784a8587711c0a343a0709f492c30e5.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "a440db839ee81af526d793cf6aa1e226b2320a16d2794e4d80ffac5372f6e7bf", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "028b80aac4406a0e41d51357ff37bac9343e321c2d855806786f090ad445a824", "generation_seconds_batch": 27.42959595506545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014590814709663391, "target_z": -0.5312500150781282, "ce": 6.205295085906982, "genuineness": 4.381826400756836, "identity": 0.8420540690422058, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a440db839ee81af526d793cf6aa1e226b2320a16d2794e4d80ffac5372f6e7bf.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "a458c6832f1e02ea9dad345e85007d0743639a22d591c97f903927f6d9add820", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "32f6d1469a7c10007ac4b7e14ef48dee9061daca51bf6eb5df2a07ad9a02ef25", "generation_seconds_batch": 24.87641819694545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03485792875289917, "target_z": -0.5781250032310274, "ce": 5.998785495758057, "genuineness": 4.3127899169921875, "identity": 0.48403018712997437, "hypothesis": "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_Sourness/a458c6832f1e02ea9dad345e85007d0743639a22d591c97f903927f6d9add820.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": "a48a51c2dfe1a76ec04f69a95c5e7f5ce9ce8800f86c14f2d78431d0d91fed11", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dbecb09140dc0d7aa8b696817b592d910df20786b4a1d600d8578016039292d4", "generation_seconds_batch": 24.589789233054034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08336693048477173, "target_z": -0.3046875091545778, "ce": 6.268836498260498, "genuineness": 4.2751336097717285, "identity": 0.5463100671768188, "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_Sourness/a48a51c2dfe1a76ec04f69a95c5e7f5ce9ce8800f86c14f2d78431d0d91fed11.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "a48aaecbd4ce1e801ea75431b6623b6c622f5bc470c3c855b9ee94894048c306", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cd23a5c0cce64c7692c08cfdd82d10f27ae2d3a7b0436c6e68fe4b187b508d39", "generation_seconds_batch": 24.720328395953402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9075630903244019, "target_z": 1.6015624456110378, "ce": 5.760505676269531, "genuineness": 3.8797430992126465, "identity": 0.10519655048847198, "hypothesis": "De deur 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_Sourness/a48aaecbd4ce1e801ea75431b6623b6c622f5bc470c3c855b9ee94894048c306.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "a4c50f548b8c57b0a182d18cd8f6d67936d2f1343b08f0dbb12d1a713d5ee308", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d33a5070e3da7b6d8a4fbfde879c8a4780c7a1b578922647bd38ef37b905e78c", "generation_seconds_batch": 18.637422558967955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09012264013290405, "target_z": -0.2890625016155137, "ce": 6.316492557525635, "genuineness": 4.055472373962402, "identity": 0.2955128848552704, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a4c50f548b8c57b0a182d18cd8f6d67936d2f1343b08f0dbb12d1a713d5ee308.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": "a4f24e3ae51d300373e7398b3ae9f72bf3cc212c8fa8a045a3288e52e06f3107", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I wrote the number on the envelope.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f823908dd86b823604d522b9f5647ae7142ad227223649ac5307f37578da88df", "generation_seconds_batch": 15.531335202045739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12727902829647064, "target_z": -0.20312499461495423, "ce": 6.23706579208374, "genuineness": 3.8797430992126465, "identity": 0.40161287784576416, "hypothesis": "I wrote the number on the envelope, read it carefully, and checked the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a4f24e3ae51d300373e7398b3ae9f72bf3cc212c8fa8a045a3288e52e06f3107.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "a4f3daea19a0e8bce0eaadcd6cb2b0cfaa3c26f01d4e6e7be26008747c1071bb", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "de491ae012cc1b1adaf80ad185e62fca2a6a17f29ad324c908f2d236c91903a2", "generation_seconds_batch": 24.514551364001818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35950642824172974, "target_z": 0.33398436382603003, "ce": 6.086154937744141, "genuineness": 4.030367851257324, "identity": 0.46614524722099304, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a4f3daea19a0e8bce0eaadcd6cb2b0cfaa3c26f01d4e6e7be26008747c1071bb.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "a54bcf877c0fdcde1628007e3d91626750456811f27a9bb3d71d8390a4c7a49b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "711cef7616da9dfaa424ead56f75ff25d0d8036891c2c4fa55f4133fa570888a", "generation_seconds_batch": 23.512240311014466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03945484757423401, "target_z": -0.40624998922990846, "ce": 6.340320587158203, "genuineness": 4.557555198669434, "identity": 0.22746679186820984, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a54bcf877c0fdcde1628007e3d91626750456811f27a9bb3d71d8390a4c7a49b.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "a5918d3e06f2b466ec4b252c067efa4a41da3c5ee944e103fb7e92541a931187", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aae5e21c754d377cf91f2645b92b3f6f9441581793b282ea1c2845b593e12362", "generation_seconds_batch": 24.135054055950604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 5.974957466125488, "genuineness": 4.143336772918701, "identity": 0.7268505692481995, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a5918d3e06f2b466ec4b252c067efa4a41da3c5ee944e103fb7e92541a931187.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "a59dbcee4bcbcb70c2dde4b8a7a6bee5aaee5a150860168fc7af4590a81328b1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "12093eab2cefda97f256194bfb0bb9e357fb13949a34b91892d45b62a17e4c0d", "generation_seconds_batch": 18.948233003960922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08505585789680481, "target_z": -0.3007812572698118, "ce": 5.871703147888184, "genuineness": 4.262581825256348, "identity": 0.5646231174468994, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a59dbcee4bcbcb70c2dde4b8a7a6bee5aaee5a150860168fc7af4590a81328b1.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "a5c5407251f2e88ed4669e8d5b39dfb4ac19c20b954e1490a72afa7de5fd514e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "77b7a4bb2dcbb3d46b8750cc7091ea642497592166a58334c8973c4cdab9dff1", "generation_seconds_batch": 24.526551779010333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38906264305114746, "target_z": 0.40234373734514245, "ce": 5.780362129211426, "genuineness": 3.936227321624756, "identity": 0.10486399382352829, "hypothesis": "Ik 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_Sourness/a5c5407251f2e88ed4669e8d5b39dfb4ac19c20b954e1490a72afa7de5fd514e.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "a62fcd94f41880df0ba92b6fad1fce89851a3038f5c3460cce4c00bf391b7c9a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5a9a2d76e520dad745847a294f5a24187a7aee78b897fbc583d2b3666f25855e", "generation_seconds_batch": 23.910610068007372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054655179381370544, "target_z": -0.3710937567313072, "ce": 5.855817794799805, "genuineness": 4.306513786315918, "identity": 0.5252255797386169, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a62fcd94f41880df0ba92b6fad1fce89851a3038f5c3460cce4c00bf391b7c9a.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": "a6d0f584f1883dc9b83fc186de76087cf08c2b5fdae5d0b08f42a6d7a9e9bc32", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Someone moved the little blue chair.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1897ea8752523fa03a5932ba1bea3fdd710b607d2b6572e328bb7162e75657a9", "generation_seconds_batch": 15.617330713081174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11883439123630524, "target_z": -0.22265625403878433, "ce": 6.403861999511719, "genuineness": 4.419482707977295, "identity": 0.35371947288513184, "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_Sourness/a6d0f584f1883dc9b83fc186de76087cf08c2b5fdae5d0b08f42a6d7a9e9bc32.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "a6f23ba18196b48916108472e42dc07b9bd48396233afa08e9b9a0db9236088f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ef74a64d728cd409ca2a94da3ca1810cf4d91f1bd405452e9f7d64933a45293a", "generation_seconds_batch": 23.22317368199583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0039873868227005005, "target_z": -0.48828124434570197, "ce": 6.181467056274414, "genuineness": 4.381826400756836, "identity": 0.4244037866592407, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a6f23ba18196b48916108472e42dc07b9bd48396233afa08e9b9a0db9236088f.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "a7d9d627834321137884a19e18dbadbec969977d86dbc333ddeadfe470226116", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2dc1f840646145d10211e1c9fad04224d7e0171c8e2d8b18d52cba6ec93d4634", "generation_seconds_batch": 24.729894953081384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09856727719306946, "target_z": -0.2695312421916836, "ce": 5.982900142669678, "genuineness": 4.030367851257324, "identity": 0.39235615730285645, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a7d9d627834321137884a19e18dbadbec969977d86dbc333ddeadfe470226116.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "a7e99b12003af8cf133ba5996b777651a9c015f1eee2f10c67f561206f82e88f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f8177fd9397d57420617416b8a8122b74dfa84414ec6be6ebde5b18c094cdf60", "generation_seconds_batch": 30.301184987998568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20159178972244263, "target_z": -0.03125001507812814, "ce": 6.070269584655762, "genuineness": 4.15588903427124, "identity": 0.49922144412994385, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a7e99b12003af8cf133ba5996b777651a9c015f1eee2f10c67f561206f82e88f.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": "a83820af5deacb268cb54784e0faaa6d80b0d78034d7018a9f9853e9ad82bdbc", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "035075d35caf0cb4c383f1f1cbe6157ce59c5270b3860f9429a672406fe2b7ed", "generation_seconds_batch": 14.50711557304021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09603388607501984, "target_z": -0.2753906200188327, "ce": 6.316492557525635, "genuineness": 4.231201171875, "identity": 0.6220910549163818, "hypothesis": "De sleutels liggen op de keukentafel. Ik ik in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a83820af5deacb268cb54784e0faaa6d80b0d78034d7018a9f9853e9ad82bdbc.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "a877c87090571a60bbe8c22ac3e564c3fd2d8467d27748d126d8a3dc813f5c17", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1e85ad3d1f9514632784408617d0de5e3c06eac5d916c369addf2969d76cc4b7", "generation_seconds_batch": 24.987188157974742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40764084458351135, "target_z": 0.44531250807756867, "ce": 5.974957466125488, "genuineness": 4.21237325668335, "identity": 0.698311448097229, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a877c87090571a60bbe8c22ac3e564c3fd2d8467d27748d126d8a3dc813f5c17.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "a8acd41fa3560cb046445828bb236adc179db4e17bd3edbb800425a1db5ac4f9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "feeca9b048d0b2b862d8d65d11cf9fd823b64bf159accaa3d490cd88c33c0880", "generation_seconds_batch": 25.44204349606298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0006095319986343384, "target_z": -0.496093748115234, "ce": 6.23706579208374, "genuineness": 4.231201171875, "identity": 0.7522784471511841, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a8acd41fa3560cb046445828bb236adc179db4e17bd3edbb800425a1db5ac4f9.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "a8b8ecc09b71f9da82f81a247f6f8b41ef14876a37001bb43d3bd381b76d8d97", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f326c6cbdb146fdb434bc9858f372352951e1e26890eb765435f58395e741180", "generation_seconds_batch": 22.990764061920345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009524032473564148, "target_z": -0.51953125942383, "ce": 6.221180438995361, "genuineness": 3.898571252822876, "identity": 0.3868057131767273, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a8b8ecc09b71f9da82f81a247f6f8b41ef14876a37001bb43d3bd381b76d8d97.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "b0828b84eafe42a13c88f1de0ab0e6d2521d65b1fbf15b9af7f7b4d403b5bb86", "generation_seconds_batch": 17.13628765696194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 6.149696350097656, "genuineness": 4.507347106933594, "identity": 0.7142409682273865, "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_Sourness/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "a8fc9dc58f5bc7be3bd869b31473459aab7cee841f157a959edbdc6687aa5f52", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cf1a3ebafa27251f960925f6732fe3220a7157285ca784c0a4a86791558ebe8f", "generation_seconds_batch": 20.38611501606647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09012264013290405, "target_z": -0.2890625016155137, "ce": 6.173524379730225, "genuineness": 4.093128204345703, "identity": 0.4881783127784729, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a8fc9dc58f5bc7be3bd869b31473459aab7cee841f157a959edbdc6687aa5f52.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "b57230ab23d5e833e8e5bdcbafafb824d484ac7193ee6a871966e5b3bf08394f", "generation_seconds_batch": 17.417397539014928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06732213497161865, "target_z": -0.34179686759556205, "ce": 6.229123115539551, "genuineness": 4.557555198669434, "identity": 0.759950578212738, "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_Sourness/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "a954bab4e37d744d993ed7ab48206a8317269de69e5fc8aa64271cf4bfa60537", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8e987784f1bef2aa856c92918019da598b49978abda66bd04d31648c68c05202", "generation_seconds_batch": 23.049762167036533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07998907566070557, "target_z": -0.31250001292410984, "ce": 6.181467056274414, "genuineness": 4.017816066741943, "identity": 0.33970433473587036, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a954bab4e37d744d993ed7ab48206a8317269de69e5fc8aa64271cf4bfa60537.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "a9adea08c85929e5df87a6916d234e21410ceedc0f6953d136c42a12df54ad5d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7f559c3235c967a6f6a53b523f6021b26397fa382a2246e92a466cd4551b3b65", "generation_seconds_batch": 24.45451825996861, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25394850969314575, "target_z": 0.08984372442103263, "ce": 5.935244083404541, "genuineness": 3.8922953605651855, "identity": 0.41843438148498535, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a9adea08c85929e5df87a6916d234e21410ceedc0f6953d136c42a12df54ad5d.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "a9bc53333bd5135cf826495c31d283090d09705fbfe98d8f5f9d39e34cf60ea7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e7551a801260e30904eca84c30074663dfb60c449266f14ebed8d4127bacdecc", "generation_seconds_batch": 24.005008123000152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22354784607887268, "target_z": 0.019531259423830088, "ce": 6.046441555023193, "genuineness": 4.306513786315918, "identity": 0.46387994289398193, "hypothesis": "De deur 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_Sourness/a9bc53333bd5135cf826495c31d283090d09705fbfe98d8f5f9d39e34cf60ea7.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "a9d77aee6e0e34fed4a07c3933f7bd64627992db66701c5b09d76bb9843e1349", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5dfdb29bdadec889b5f6689964b589169d76f29e5b089048ded68d7e5fcd020f", "generation_seconds_batch": 24.515852708020248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0039873868227005005, "target_z": -0.48828124434570197, "ce": 6.348263263702393, "genuineness": 4.030367851257324, "identity": 0.3940993547439575, "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_Sourness/a9d77aee6e0e34fed4a07c3933f7bd64627992db66701c5b09d76bb9843e1349.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "a9e07ca424d1bb1ca78953c8b7d0221ae8a925eaafc22a7e838ec2f80b01ae89", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3b45dfb1c8958b126d0b3f62c03ba49ac6611acd68996df0ebdc00db40ccab15", "generation_seconds_batch": 22.73332710005343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1762578934431076, "target_z": -0.08984375888532552, "ce": 6.062326908111572, "genuineness": 4.118232727050781, "identity": 0.5648897886276245, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a9e07ca424d1bb1ca78953c8b7d0221ae8a925eaafc22a7e838ec2f80b01ae89.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "a9ec13e147a8bb3f49925fb9adf1e3650b203b6177b4b9eb3c89a3a23e820ebf", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "202c05756b4b6783fe5d43f743321fcb5c0f5b18bf26b0359d6d2ac62657c75d", "generation_seconds_batch": 21.96192857204005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12390117347240448, "target_z": -0.21093749838448628, "ce": 5.95112943649292, "genuineness": 4.287685871124268, "identity": 0.8278809785842896, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a9ec13e147a8bb3f49925fb9adf1e3650b203b6177b4b9eb3c89a3a23e820ebf.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "a9fa0f77f37db9dc4dda0a26662c3e3e410ab4304c38cf6243bc7203b51e5baa", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6883980b181efa5b404dc3da58866c66027c2e13260a5bd58e8a82eb4e8baa12", "generation_seconds_batch": 25.610020303050987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054655179381370544, "target_z": -0.3710937567313072, "ce": 6.117925643920898, "genuineness": 4.287685871124268, "identity": 0.5924156308174133, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/a9fa0f77f37db9dc4dda0a26662c3e3e410ab4304c38cf6243bc7203b51e5baa.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "aaf42c6fa424431d284b20159aa21ca24d0ce760eb9c9d72ed137a165cc11cd9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "493c1e01a553e2abc55437c8a7255d642b7d84a0e9b7cd0be7b0938034068a7b", "generation_seconds_batch": 24.161355814081617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09603388607501984, "target_z": -0.2753906200188327, "ce": 6.149696350097656, "genuineness": 4.557555198669434, "identity": 0.6256285309791565, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/aaf42c6fa424431d284b20159aa21ca24d0ce760eb9c9d72ed137a165cc11cd9.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "ab3855dafc90e18776093a4a8077e3a7f4ad83bb1f5a24f2be0bdd3cab594357", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "693d261a64cd2804c809fb5820116ecd03c77675f717672cf0417e2e2c62b523", "generation_seconds_batch": 16.165709855034947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.04668042063713074, "target_z": -0.6054687664243896, "ce": 5.935244083404541, "genuineness": 4.281409740447998, "identity": 0.36680200695991516, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ab3855dafc90e18776093a4a8077e3a7f4ad83bb1f5a24f2be0bdd3cab594357.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "e69f27e71616f24cff802381f54ebe5acc5fab5236cc1cb2abf3a83af6987432", "generation_seconds_batch": 15.371118218055926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 6.499174118041992, "genuineness": 4.268857479095459, "identity": 0.3748965263366699, "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_Sourness/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "abae6070260ac515cbfc894e4189a69fa81bac28b4511b9bf10ba67893cbca27", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d3b99b8bd911b10d1164efc172dc4b20e9911cc027f7a10d22440b8bfa360307", "generation_seconds_batch": 22.15783742093481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1661243438720703, "target_z": -0.11328123572962873, "ce": 6.125868320465088, "genuineness": 4.344170093536377, "identity": 0.3569643795490265, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/abae6070260ac515cbfc894e4189a69fa81bac28b4511b9bf10ba67893cbca27.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": "ac06217f638f588456e5f2a6aa9ca1b284ba1341f290e39ced8b5a4a98834e46", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "434f2d462a636a7668e8623caaab3b356b68c68bdfc95a75cb5a57b0c8dbf298", "generation_seconds_batch": 15.473287367960438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.301238477230072, "target_z": 0.1992187771944811, "ce": 6.252951145172119, "genuineness": 4.017816066741943, "identity": 0.36322879791259766, "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_Sourness/ac06217f638f588456e5f2a6aa9ca1b284ba1341f290e39ced8b5a4a98834e46.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "ac4804615fb7535c1ec11e1bb7a3f47a455222516ccdd2caf899f49098bcc132", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "be5ad6359c58d7287a7baa24909ceeaa91a2800ebc461eb83ac5ebd8560c0ee3", "generation_seconds_batch": 16.758592555997893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.395919322967529, "genuineness": 4.231201171875, "identity": 0.47703492641448975, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ac4804615fb7535c1ec11e1bb7a3f47a455222516ccdd2caf899f49098bcc132.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "ac6bf6ec54b299354b9ca4eee23c92ec7988a0c91ec614a298a342fea3b2a3c7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "17eac157fae0b653e0099df752b18fbd1ff6f6b8d58ef038feadb48a23615628", "generation_seconds_batch": 17.71890732110478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.491931676864624, "target_z": 2.953124908454222, "ce": 5.911416053771973, "genuineness": 3.6789097785949707, "identity": 0.6688129901885986, "hypothesis": "Ik 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_Sourness/ac6bf6ec54b299354b9ca4eee23c92ec7988a0c91ec614a298a342fea3b2a3c7.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "ac9c432ab24f494816b828fb3eaaec9e0655c73ccc1e2da8b4f686cb0ac40485", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b7d27f790d5001f195f6bc1abf5f39ada1d114e02e4b485508d5f9037e15298b", "generation_seconds_batch": 25.343290459015407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019187718629837036, "target_z": -0.4531250118471007, "ce": 6.173524379730225, "genuineness": 4.419482707977295, "identity": 0.5086715817451477, "hypothesis": "J'ai trouvé la 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_Sourness/ac9c432ab24f494816b828fb3eaaec9e0655c73ccc1e2da8b4f686cb0ac40485.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "ad5499b9f305f920491a75b1441fd7942b07c08eee0078b11db7f52c87045d13", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "12e8c2ea2ff59e6b1b7df205a954fd64357370a52d89336949bc9a529c3bd4ac", "generation_seconds_batch": 16.495066358940676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11123422533273697, "target_z": -0.24023437028808495, "ce": 6.252951145172119, "genuineness": 4.168440818786621, "identity": 0.5831539630889893, "hypothesis": "Ik 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_Sourness/ad5499b9f305f920491a75b1441fd7942b07c08eee0078b11db7f52c87045d13.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": "ad6594c25a596d3b8ad1b8b0073857a0fcca93dd0fd0a97849de9f1601315e51", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9597810bded931ec67732e333ae0ec7808c69b32d516fe659e9b5e51af566145", "generation_seconds_batch": 14.42911142797675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019187718629837036, "target_z": -0.4531250118471007, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.6365251541137695, "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_Sourness/ad6594c25a596d3b8ad1b8b0073857a0fcca93dd0fd0a97849de9f1601315e51.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "ad6cf7046ade2309e3e4471638ad04d4844844f4bc88adb7f732236bc4b0a532", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e4893429d2f07870c0ed78d6f46ac7508c65fa701e293d2f211fe8639146e9d7", "generation_seconds_batch": 22.89211208699271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016279742121696472, "target_z": -0.5351562669628942, "ce": 6.141753673553467, "genuineness": 4.545003414154053, "identity": 0.7251837253570557, "hypothesis": "J'ai trouvé la 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_Sourness/ad6cf7046ade2309e3e4471638ad04d4844844f4bc88adb7f732236bc4b0a532.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "adb2d3a7a57a04115e23dd7774c6795334691c3cbe8c8c931a064844165a8f9a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "884142d4dc07204a93d80f2fc36e05cbe41bfb4bc3bff0c65f584de35693dfc1", "generation_seconds_batch": 24.36039363697637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019187718629837036, "target_z": -0.4531250118471007, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.5626783967018127, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/adb2d3a7a57a04115e23dd7774c6795334691c3cbe8c8c931a064844165a8f9a.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "adc17c004dbf3a39488cfd39fd75956813e70cab2fe0e4aadaa1e3114dfaa580", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3b0de7551dac044fbe4f494c95605a30ee01f426b56deb5c98ebd70a6a98d73f", "generation_seconds_batch": 16.09426728100516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04029931128025055, "target_z": -0.40429686328752545, "ce": 6.24500846862793, "genuineness": 4.68307638168335, "identity": 0.6236541271209717, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/adc17c004dbf3a39488cfd39fd75956813e70cab2fe0e4aadaa1e3114dfaa580.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "1431583abe8b3c899bcb471ddd881604cadd6af7998a0ec110ff9ee38a302c70", "generation_seconds_batch": 17.284028002992272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16527986526489258, "target_z": -0.11523439613630462, "ce": 6.133810997009277, "genuineness": 4.381826400756836, "identity": 0.6338106393814087, "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_Sourness/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "ade9e7520498c7062e4ffc797d74e07682683a8f87cba1fbf7d4d2240127df89", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "60a0308a3f99b9593dfc69d570a831407e629e4c07c4c7318a07fc5007665eeb", "generation_seconds_batch": 21.982353833969682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3230390548706055, "target_z": 2.5624999956919634, "ce": 6.348263263702393, "genuineness": 4.419482707977295, "identity": 0.6098698973655701, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ade9e7520498c7062e4ffc797d74e07682683a8f87cba1fbf7d4d2240127df89.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "fb00dd8a46986feeb705c4ded2fd9de161a5c3d59284bc83031b69bec081805b", "generation_seconds_batch": 16.436208595056087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0808335393667221, "target_z": -0.31054688698172683, "ce": 6.403861999511719, "genuineness": 3.9927117824554443, "identity": 0.20887914299964905, "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_Sourness/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "ae8a01b1466e90d3decc6e1b0a7c49bd3b2f45b308afa772bbb8104bf48209e7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e1e311950e0c9289320e0fd306d921bcace03c6c2af9e955776d346dc596a649", "generation_seconds_batch": 25.22348839393817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09856727719306946, "target_z": -0.2695312421916836, "ce": 6.070269584655762, "genuineness": 4.093128204345703, "identity": 0.5959445238113403, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ae8a01b1466e90d3decc6e1b0a7c49bd3b2f45b308afa772bbb8104bf48209e7.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": "aeb738a741f4545cd93ea576b2b341535173c9800d07f8033918f7d9416a6475", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a97bc3588118bfee7ed9e6307b52268c62a8a54d7f9072aecc474b39512b9d1", "generation_seconds_batch": 18.568382801953703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04621054232120514, "target_z": -0.3906250161551373, "ce": 6.165581703186035, "genuineness": 4.124508857727051, "identity": 0.725446343421936, "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_Sourness/aeb738a741f4545cd93ea576b2b341535173c9800d07f8033918f7d9416a6475.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "af186925c1d3fed004693b77490b9a0cf666dfa3ede3734de8409b81bed2ec4b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7c7cdf4b827e676494e7a6ca6bea3f88518c2a4fd0aba3ae2d10c000507c2f8e", "generation_seconds_batch": 27.29190336097963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09687834978103638, "target_z": -0.2734374940764497, "ce": 5.7128496170043945, "genuineness": 3.9801597595214844, "identity": 0.5959751009941101, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/af186925c1d3fed004693b77490b9a0cf666dfa3ede3734de8409b81bed2ec4b.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "af398ddc0a6f0dabf6cbbeee6440e815545140b41585a2801c69933b4fa358ba", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5e55d0f7043ee2ef29240cb36799e9b85e535f838fc31f2e9325076a43173b03", "generation_seconds_batch": 18.19853241799865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4194633364677429, "target_z": 0.4726562712709308, "ce": 5.974957466125488, "genuineness": 4.231201171875, "identity": 0.7124055624008179, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/af398ddc0a6f0dabf6cbbeee6440e815545140b41585a2801c69933b4fa358ba.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "af83f4f878b8eeffee70019635384380312570e135fe07d72ae3fc4c375e6c3f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "eed873c66134c1a08b3586d42122fe959e9aeed0160f53fca275bf787443888c", "generation_seconds_batch": 24.526551779010333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18976931273937225, "target_z": -0.05859374380719737, "ce": 5.903473377227783, "genuineness": 4.061748504638672, "identity": 0.6681340932846069, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/af83f4f878b8eeffee70019635384380312570e135fe07d72ae3fc4c375e6c3f.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": "af9f336e831456c6c166c6ee5201374ed52c9ff2a9c4edb66e2cd08f0cffb17a", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34a490388a1d9fabc289f193f62a6ed42506c595397d919fb5ef0d9e35b40944", "generation_seconds_batch": 26.929674881976098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03945484757423401, "target_z": -0.40624998922990846, "ce": 6.173524379730225, "genuineness": 4.356721878051758, "identity": 0.6000871658325195, "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_Sourness/af9f336e831456c6c166c6ee5201374ed52c9ff2a9c4edb66e2cd08f0cffb17a.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": "afdaa1ed202c14be1538aa4d7f34af44a59754f3f77ecb6023003c0f800e1a7f", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6cfc0a8d45afbb8008801a4b3b346dd3b77ede46aa698bcfc6f589bf0f7bbb8f", "generation_seconds_batch": 19.489648286020383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016279742121696472, "target_z": -0.5351562669628942, "ce": 6.24500846862793, "genuineness": 4.394378662109375, "identity": 0.7101045846939087, "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_Sourness/afdaa1ed202c14be1538aa4d7f34af44a59754f3f77ecb6023003c0f800e1a7f.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "aff7121a41250d9ccc9bb935018955e53856d061d23835ce2e94c7ba94523179", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "246edd0768146176e56fcc1d4da89afb10dd009bf535e805868c05d2cd543b8c", "generation_seconds_batch": 23.800385601934977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028476819396018982, "target_z": -0.4316406264808876, "ce": 6.157639026641846, "genuineness": 4.375550270080566, "identity": 0.4591074585914612, "hypothesis": "J'ai trouvé la 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_Sourness/aff7121a41250d9ccc9bb935018955e53856d061d23835ce2e94c7ba94523179.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "b00212157324c2e3462a7825a87b436d81dbe517fac4ce72fd239f59825474aa", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ec4abd408ea110e64333eb1a13194800f34c796744ecc33ebc51d38387d994d4", "generation_seconds_batch": 22.392845108988695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32235005497932434, "target_z": 0.24804689128976343, "ce": 6.141753673553467, "genuineness": 4.017816066741943, "identity": 0.6550156474113464, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b00212157324c2e3462a7825a87b436d81dbe517fac4ce72fd239f59825474aa.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "b012cfe11e90de7d47d3ca97de7d72b88ec5fa4561aee36df92e929f5dd1a753", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "892afc2ac150b8a7799bff18f0526d30fec26eee2e0e773b497d581a1bd0dd3b", "generation_seconds_batch": 17.817381756030954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0056763142347335815, "target_z": -0.4843749924609359, "ce": 6.324435234069824, "genuineness": 4.2249250411987305, "identity": 0.3070591688156128, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b012cfe11e90de7d47d3ca97de7d72b88ec5fa4561aee36df92e929f5dd1a753.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "b0a70a8c4c93f2b8b76b10428efd22d6ddbd38a7161949d6afc96d3dc468e1a0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fb22d7e6948095a8e4be63e3042a7ba152acd24769a361b1652881859aea2d28", "generation_seconds_batch": 23.547983691096306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035232529044151306, "target_z": -0.41601561894182354, "ce": 5.919358730316162, "genuineness": 4.457139015197754, "identity": 0.6724226474761963, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b0a70a8c4c93f2b8b76b10428efd22d6ddbd38a7161949d6afc96d3dc468e1a0.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "b0bc941a34f69d60d6c3be1a6faf010b73d8957bbab14a465ba63b5f6cb7c493", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b9232ec245cb5bc8a3ddb26e5f7794dbd6e4d0671fd74a3fd4f66008a9c70f5b", "generation_seconds_batch": 32.96372454997618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1323457956314087, "target_z": -0.19140627342494906, "ce": 6.006728172302246, "genuineness": 4.369274139404297, "identity": 0.621894121170044, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b0bc941a34f69d60d6c3be1a6faf010b73d8957bbab14a465ba63b5f6cb7c493.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "b140a20a7eef62c1c0415a898ed3800f4d5f885f06f349d5e55dafed6edef327", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3dce210c365a873a40bc243b7ee45f7a78d21f83de05d47627d55a12e66d289c", "generation_seconds_batch": 27.802313773077913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4735089838504791, "target_z": 0.5976562626548575, "ce": 5.411027908325195, "genuineness": 3.7416701316833496, "identity": 0.34782177209854126, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b140a20a7eef62c1c0415a898ed3800f4d5f885f06f349d5e55dafed6edef327.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": "b1410075dd528808eed5d01424ceacc91de1a0f68ba1cce3950517c68eb51314", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Escribí el número en el sobre.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "52effd89913277f457dc6ef9673b28d68c62bcf9c05192c04e314bdc39c8cf68", "generation_seconds_batch": 14.429744503926486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054655179381370544, "target_z": -0.3710937567313072, "ce": 6.3641486167907715, "genuineness": 4.3127899169921875, "identity": 0.6859184503555298, "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_Sourness/b1410075dd528808eed5d01424ceacc91de1a0f68ba1cce3950517c68eb51314.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": "b17e7f88f1478962267dac222584c22d1da43a38fb432baf25ec51eca54acc31", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The keys are on the kitchen table.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab89fc9cd3539009d2d6af2dc42c0e74b401b0c25f73fea9e98ed1140e13bff2", "generation_seconds_batch": 19.099727941094898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04029931128025055, "target_z": -0.40429686328752545, "ce": 6.403861999511719, "genuineness": 4.545003414154053, "identity": 0.36010509729385376, "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_Sourness/b17e7f88f1478962267dac222584c22d1da43a38fb432baf25ec51eca54acc31.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "b1b405e2920082e1ff42183cc9e3deda4d665738914714fbcf3f865d527ab6d8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a284eee8f2808cb0c0d8deaec8089c926823139c1a6460381931cd53ec3d4d3", "generation_seconds_batch": 26.810802590101957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006146177649497986, "target_z": -0.511718755654298, "ce": 6.173524379730225, "genuineness": 4.607763767242432, "identity": 0.7810956835746765, "hypothesis": "J'ai trouvé la 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_Sourness/b1b405e2920082e1ff42183cc9e3deda4d665738914714fbcf3f865d527ab6d8.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "b1c317d1f4ccbdcfe544a0158a11e197ca585b8f3ba0d4c82d7615efbcfee34c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "79738cb99dacbcafdfb3553041b9476f077a919683a4ca28b8df39953e762bed", "generation_seconds_batch": 23.776870236033574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11207868903875351, "target_z": -0.23828124434570194, "ce": 5.927301406860352, "genuineness": 4.017816066741943, "identity": 0.6154187917709351, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b1c317d1f4ccbdcfe544a0158a11e197ca585b8f3ba0d4c82d7615efbcfee34c.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "b1c8e3a8a689aaa7dc52ac9b2e9c0d844754d20b8a1f028e7833c1bfed481207", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fe9679e5f7ea10d17c423dcdf79ae75e3f22accb54e8166701d6fedbc379bb3e", "generation_seconds_batch": 22.990764061920345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0006095319986343384, "target_z": -0.496093748115234, "ce": 6.292664527893066, "genuineness": 4.18726921081543, "identity": 0.45736438035964966, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b1c8e3a8a689aaa7dc52ac9b2e9c0d844754d20b8a1f028e7833c1bfed481207.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "b21a897470fa19fa346cf2d944a01945b277a200daf3266b93ef413a6be053cc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2ea57b4f2a03b57d4e980b6f23faef21130f3cb246349415f4d921c84d9f8011", "generation_seconds_batch": 23.49852873501368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01290188729763031, "target_z": -0.5273437631933621, "ce": 6.395919322967529, "genuineness": 4.3127899169921875, "identity": 0.45396608114242554, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b21a897470fa19fa346cf2d944a01945b277a200daf3266b93ef413a6be053cc.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": "b23994abaa52d32da5a1f3a6ce21559b1ebe36d8548b1acb207b03ad7bcd42eb", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa22f042acb59ed3f07ac4441e35bc88cffa88b02a8ffc148407c94739ff8ca3", "generation_seconds_batch": 26.929674881976098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1407904326915741, "target_z": -0.171875014001119, "ce": 6.23706579208374, "genuineness": 4.143336772918701, "identity": 0.6299721598625183, "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_Sourness/b23994abaa52d32da5a1f3a6ce21559b1ebe36d8548b1acb207b03ad7bcd42eb.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "b28b4105087e47638f746bdf279aaf2f9f4a74ce4ab7866463807be822656c41", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "874068cee73027624c00d81f09111905d043a9089a15d6dc57cd82e56008b7b1", "generation_seconds_batch": 17.518879274954088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011212959885597229, "target_z": -0.5234375113085961, "ce": 6.292664527893066, "genuineness": 4.632867813110352, "identity": 0.6251566410064697, "hypothesis": "J'ai trouvé la 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_Sourness/b28b4105087e47638f746bdf279aaf2f9f4a74ce4ab7866463807be822656c41.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "b2c91cd96a81862c58060ee83be98a3305cf39d46315ca8e848e52f57e3f4057", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cbf90ebe39421b464cc5ebdb413b60b558cc110091fbb26e5339d6a26140e2f8", "generation_seconds_batch": 19.036507615004666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6880026459693909, "target_z": 1.0937499763057987, "ce": 5.879645347595215, "genuineness": 3.8044304847717285, "identity": 0.1500455141067505, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b2c91cd96a81862c58060ee83be98a3305cf39d46315ca8e848e52f57e3f4057.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "b2cfab75387ce4c0fdcdf6308f7f85135913dfeaf78e3dfcb58dfe7d07a74242", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9ed0d55eeec412d6ec5d9129f4bf45695af52a37cf30aade45cd2ac549b79c72", "generation_seconds_batch": 18.947562271961942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01796865463256836, "target_z": -0.5390624843833672, "ce": 6.24500846862793, "genuineness": 4.15588903427124, "identity": 0.5283759832382202, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b2cfab75387ce4c0fdcdf6308f7f85135913dfeaf78e3dfcb58dfe7d07a74242.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "b2feed7b9fda8603c7b3ae96c85de2a1533e656bde7269f0eea31a9bd5154f25", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "393569560e43b3b237a3f23cd779c8ad0802294adade843e77a70ef6e9599ce5", "generation_seconds_batch": 23.6728927110089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25563743710517883, "target_z": 0.09374997630579864, "ce": 5.744620323181152, "genuineness": 4.024092197418213, "identity": 0.4833841323852539, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b2feed7b9fda8603c7b3ae96c85de2a1533e656bde7269f0eea31a9bd5154f25.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "b3665f73c3e40af2ec788c764062acd18caf44034ae8fa550634208083341249", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fd708d2904eee2de303b9573e93fe5f90ba442ecded5f884002572f44d64e6a3", "generation_seconds_batch": 23.852399950963445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03607699275016785, "target_z": -0.4140624929994405, "ce": 6.23706579208374, "genuineness": 4.645420074462891, "identity": 0.5803728699684143, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b3665f73c3e40af2ec788c764062acd18caf44034ae8fa550634208083341249.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "1457b19e1d47826e0da8a56bb6aacd195e86d7064779c86b7180cf61d5e0b0d1", "generation_seconds_batch": 20.19896266690921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09603388607501984, "target_z": -0.2753906200188327, "ce": 6.1894097328186035, "genuineness": 4.469690799713135, "identity": 0.6568398475646973, "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_Sourness/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "b462abf1f1db2dc7f535eb11763e6f1620899e05cdb036bed8ed0abb587d52d8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f43f2119e68bcca355802b656a1700aae809bfa9e10c9ceb75f0e9cf6abe0d65", "generation_seconds_batch": 25.76587558502797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030165746808052063, "target_z": -0.42773437459612157, "ce": 6.038498878479004, "genuineness": 4.457139015197754, "identity": 0.4831266701221466, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b462abf1f1db2dc7f535eb11763e6f1620899e05cdb036bed8ed0abb587d52d8.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "b46bf3d5f7a7a32c9c802945b3dd700d3c45cd1370ef04b815b5276c6b8afd9a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b36bbc1a29d35fcb3d1304cd6690a666e3a176e47fafc86ae1ed2e00ef0ac2ee", "generation_seconds_batch": 24.036074834060855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13910150527954102, "target_z": -0.175781265885885, "ce": 5.982900142669678, "genuineness": 4.068024158477783, "identity": 0.7222908735275269, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b46bf3d5f7a7a32c9c802945b3dd700d3c45cd1370ef04b815b5276c6b8afd9a.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "b46f1628b8c97fabcd2df876a8c10466d3a1a20e261b0c8bb74fdf06b63ea055", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c3d241873e8098d06fb7f7c1ab4dd4a0bffc0b1a12bd4285ee4b4f6e95440537", "generation_seconds_batch": 20.788735862006433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3635733127593994, "target_z": 2.6562500409263476, "ce": 5.816103935241699, "genuineness": 3.9676074981689453, "identity": 0.7170964479446411, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b46f1628b8c97fabcd2df876a8c10466d3a1a20e261b0c8bb74fdf06b63ea055.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "b4af93612fb342a1ac3965a11efc0327d82df9fd0eaaf7c53d5cdf5599ffcc27", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9732d5162a0d583eb3633abaa96f9fdf496f251dc06682dbf8ff65b5607c2c1b", "generation_seconds_batch": 24.366761011071503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01965758204460144, "target_z": -0.5429687362681334, "ce": 6.284721851348877, "genuineness": 4.68307638168335, "identity": 0.6807627081871033, "hypothesis": "J'ai trouvé la 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_Sourness/b4af93612fb342a1ac3965a11efc0327d82df9fd0eaaf7c53d5cdf5599ffcc27.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "b502afde33164a641bd2d9106f6f92cf75d4503d10794b8bbd718fc21de28f13", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "312d739e97d411e83cd4f107ad7c4a6935d9c2c26a56ea0c74cbffe13254473b", "generation_seconds_batch": 18.637422558967955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06394428014755249, "target_z": -0.3496093713650941, "ce": 6.181467056274414, "genuineness": 4.017816066741943, "identity": 0.19986645877361298, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b502afde33164a641bd2d9106f6f92cf75d4503d10794b8bbd718fc21de28f13.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "b53717c21d8011606ecbe756943b9bf1f1cec412fd7960de693dd9a193aa8937", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "de950972c3e377bfc7c1df5f7562541dbb1afbbb87b8964a10f2b1a6366d517a", "generation_seconds_batch": 22.54659769393038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03148007392883301, "target_z": -0.5703124994614954, "ce": 6.117925643920898, "genuineness": 4.444586753845215, "identity": 0.7484702467918396, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b53717c21d8011606ecbe756943b9bf1f1cec412fd7960de693dd9a193aa8937.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "b5cfc9e4a957c01a9e8c1a436e9e0cad49c8bde7b22554977fcd5b118c9565a4", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6fd7e202eaaa1513df8ab78f161757297559631be9c5a2a7ffbc73c24657972a", "generation_seconds_batch": 24.071341499919072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12559010088443756, "target_z": -0.20703124649972024, "ce": 6.086154937744141, "genuineness": 4.469690799713135, "identity": 0.6717334389686584, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b5cfc9e4a957c01a9e8c1a436e9e0cad49c8bde7b22554977fcd5b118c9565a4.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "b6986ba9e22a98d4e26999a61aa2e758b69f9377ea349ed2c370703646af6fb6", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b050bfaef66a680a550ea422681b9090dcc1d24b18814ad292f84209d766920d", "generation_seconds_batch": 18.290851555066183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08421139419078827, "target_z": -0.3027343832121948, "ce": 5.935244083404541, "genuineness": 4.394378662109375, "identity": 0.5288381576538086, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b6986ba9e22a98d4e26999a61aa2e758b69f9377ea349ed2c370703646af6fb6.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "b6bae5b91e0669003599aec7407bfc1ee705296a141b4503182149d8cb3826d1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0e479b88bd605142d8a1c0dae253ebed8c264d20188dfa2ae3f90ae38873d6b5", "generation_seconds_batch": 24.435832643997855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7690711617469788, "target_z": 1.2812500667745674, "ce": 5.982900142669678, "genuineness": 3.553389072418213, "identity": 0.3490073084831238, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b6bae5b91e0669003599aec7407bfc1ee705296a141b4503182149d8cb3826d1.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "b6f9f8a549609808b4ced98e8b3f434dd449492902444c22e536da32788dbdd0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "073b9f6c252cd085e77915c350883ca9957cd5e4ee9dc03a5d650714f44e3152", "generation_seconds_batch": 22.9616155968979, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9852537512779236, "target_z": 1.7812500323102747, "ce": 5.998785495758057, "genuineness": 4.2249250411987305, "identity": 0.3776877820491791, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b6f9f8a549609808b4ced98e8b3f434dd449492902444c22e536da32788dbdd0.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": "b7f407e374410a595e9f6dce0f2b4e3ef8c10d9a70b48f4cc82f82c154dd95ce", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51ba931efda0c7dee06ab61c518d051c523325b7985c14febe0da14556c8703f", "generation_seconds_batch": 24.233708895975724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04621054232120514, "target_z": -0.3906250161551373, "ce": 6.308549880981445, "genuineness": 4.457139015197754, "identity": 0.37725645303726196, "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_Sourness/b7f407e374410a595e9f6dce0f2b4e3ef8c10d9a70b48f4cc82f82c154dd95ce.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "b80195e99dba0dd406e3308519c36da455ae6ae5f7e1a794f4383e98105ee8a6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "39045cbf1c32c7cffc1418987cd141fead8d1a60f7af207daabd2c015f0857ba", "generation_seconds_batch": 15.271214258973487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.184702530503273, "target_z": -0.07031249946149543, "ce": 5.967014789581299, "genuineness": 4.406930446624756, "identity": 0.6483924388885498, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b80195e99dba0dd406e3308519c36da455ae6ae5f7e1a794f4383e98105ee8a6.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "b854c516a9ee32cfd64603d8eed021ec45007eeb80888d7221c27a2c65a375c4", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3d5c726c099b66a46682c8a8323de4e1113935fbfdef5b4fc5ffbde920cf114c", "generation_seconds_batch": 24.44486677297391, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3628842830657959, "target_z": 0.34179686759556205, "ce": 5.959072113037109, "genuineness": 3.848362922668457, "identity": 0.6545038223266602, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b854c516a9ee32cfd64603d8eed021ec45007eeb80888d7221c27a2c65a375c4.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "b861745ecffa5dd4a9b0265417b371b3622c25f9b5ec045732852aea87be2d5f", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "defe8e1f35c0fb60b75a327794be9c1776c588e62e3352f848de76272a794551", "generation_seconds_batch": 16.495066358940676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1036340519785881, "target_z": -0.257812503769532, "ce": 6.316492557525635, "genuineness": 4.444586753845215, "identity": 0.6180033087730408, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b861745ecffa5dd4a9b0265417b371b3622c25f9b5ec045732852aea87be2d5f.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": "b876b5f54f612d13a73aeea3f34a570b39ef0b6d3d4efe99fddae7bf8b7eea3d", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80cae4b1adbdfd66f3fc8c1057c88bd5032b3e9eb8b6947a50aabcca1e848f4b", "generation_seconds_batch": 19.573650588979945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028476819396018982, "target_z": -0.4316406264808876, "ce": 6.348263263702393, "genuineness": 4.3504462242126465, "identity": 0.6548162698745728, "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_Sourness/b876b5f54f612d13a73aeea3f34a570b39ef0b6d3d4efe99fddae7bf8b7eea3d.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": "b884689fe091858e22b6fcfab1fef45ff9cf125bc90162375d320a3621cf90fb", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Someone moved the little blue chair.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d8a0bda07a640fbe8bd0d0bfbc79867ccc2884460386d221612d9641411ee96", "generation_seconds_batch": 15.617330713081174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10532297939062119, "target_z": -0.253906251884766, "ce": 6.372091293334961, "genuineness": 4.243753433227539, "identity": 0.5350683927536011, "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_Sourness/b884689fe091858e22b6fcfab1fef45ff9cf125bc90162375d320a3621cf90fb.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "b941be9498316fc90ef132da59f03f55e0ee67a080ca51e03cb1813f220f81c7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0efdee4741b574a1b428dc0ffbe8a57ee9a670f12fe12275ddc022375fa3dd92", "generation_seconds_batch": 23.403234907076694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04452162981033325, "target_z": -0.39453123357561043, "ce": 5.847874641418457, "genuineness": 4.162164688110352, "identity": 0.6930453777313232, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b941be9498316fc90ef132da59f03f55e0ee67a080ca51e03cb1813f220f81c7.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "b95ad20cf080e44191720049b9e9ea1ab65f6c12aa04e9f70c5838edcc8cefea", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8e8803fa272ee1964d88974b77917d969c1958a6d586f3dd33ed1ca79d93dd83", "generation_seconds_batch": 21.855871148989536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05972196161746979, "target_z": -0.35937500107700915, "ce": 6.205295085906982, "genuineness": 4.494794845581055, "identity": 0.6381797790527344, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b95ad20cf080e44191720049b9e9ea1ab65f6c12aa04e9f70c5838edcc8cefea.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "b97d24eddcba11721a44876f6e57f73ff0e8d4039114f4276e02253ca3843c5d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f4d52e4deab1db16ce5cfad0e1266ddec3719ae1969dc9ad218c2411b8c57738", "generation_seconds_batch": 16.328655909979716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1222122460603714, "target_z": -0.2148437502692523, "ce": 6.284721851348877, "genuineness": 4.306513786315918, "identity": 0.7488387823104858, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b97d24eddcba11721a44876f6e57f73ff0e8d4039114f4276e02253ca3843c5d.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "b986e47b8989c8ee2ab8991cefea807dc5965386440d9f8e7250e3407d7a7c5a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "aa1dd1eaf816f10ed62084a740fc0e5609b27ebb72bb0db838d62ace4d2fe9bc", "generation_seconds_batch": 24.936348365969025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14585721492767334, "target_z": -0.16015625834682093, "ce": 6.09409761428833, "genuineness": 4.111956596374512, "identity": 0.6810665726661682, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b986e47b8989c8ee2ab8991cefea807dc5965386440d9f8e7250e3407d7a7c5a.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "b9881840bc577ff171d3b2e5c8ab49bd4078c2b094562406130b2b8c135c12dc", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7acc01ed2d64b4817ffbecdc89998b704f91eb616e6eee8c67657273a6ddf13c", "generation_seconds_batch": 16.03644242999144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15430185198783875, "target_z": -0.14062499892299085, "ce": 6.022613525390625, "genuineness": 4.1998209953308105, "identity": 0.6479828357696533, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b9881840bc577ff171d3b2e5c8ab49bd4078c2b094562406130b2b8c135c12dc.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "b9b451bb5f4d9d8dbcb2b09f4b04f8079234ae709f4e878686ad0bef4e4f3e50", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7b354ac9178ab3c6156273e65f120518c23564201046c186c055af1c6dcfbda6", "generation_seconds_batch": 24.161355814081617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0909671038389206, "target_z": -0.2871093756731307, "ce": 6.038498878479004, "genuineness": 4.193545341491699, "identity": 0.5407047271728516, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/b9b451bb5f4d9d8dbcb2b09f4b04f8079234ae709f4e878686ad0bef4e4f3e50.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "ba0a81e7ab2d367e61c45389d75a67694ef31a182991a4bda4a5433df275347e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "517aaf54aa60faafd6fba0af10dda06b93e3bb2d4829e5fc220a5bd1e06d4eb5", "generation_seconds_batch": 20.57722041301895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2012808322906494, "target_z": 4.59374987291292, "ce": 5.34748649597168, "genuineness": 3.3745219707489014, "identity": 0.4502168893814087, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ba0a81e7ab2d367e61c45389d75a67694ef31a182991a4bda4a5433df275347e.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "ba6b6897bb208782b5e14488a9814e0f528c4b5be47aff80d68bbeedb386c16a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7cf81b77fe969d9beecbf9eba326bba6267adc9e515f1e0f6e30dfff0047eac4", "generation_seconds_batch": 20.632799664977938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5444439053535461, "target_z": 0.7617187728864445, "ce": 6.062326908111572, "genuineness": 4.18099308013916, "identity": 0.4919629395008087, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ba6b6897bb208782b5e14488a9814e0f528c4b5be47aff80d68bbeedb386c16a.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "39fb549f3ee17358b1d65b856b5399a703452a3af2ca763d526ed4a59b9ece6b", "generation_seconds_batch": 17.671590415993705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04283270239830017, "target_z": -0.39843748546037644, "ce": 6.181467056274414, "genuineness": 4.595211505889893, "identity": 0.7141331434249878, "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_Sourness/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "ba88fb952c3f26559a83c4c75bc9873cc05d706596c1cd0481163831c710b614", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5628bef2a9703112f692aa61dcfae95ad022776a1404a3372dd1e0ffa378553b", "generation_seconds_batch": 25.006969840964302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22523677349090576, "target_z": 0.023437511308596105, "ce": 5.855817794799805, "genuineness": 4.13078498840332, "identity": 0.4554218351840973, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ba88fb952c3f26559a83c4c75bc9873cc05d706596c1cd0481163831c710b614.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "badc21acb3ce944684a0a6f857686b056c7f5c55299677cb4dbaf368599f0b77", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "feae2b53922787f771733f19fa66636d488e708ece2cb7a08e8def473ab041f2", "generation_seconds_batch": 23.785128592979163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01290188729763031, "target_z": -0.5273437631933621, "ce": 6.300607204437256, "genuineness": 4.394378662109375, "identity": 0.4812423586845398, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/badc21acb3ce944684a0a6f857686b056c7f5c55299677cb4dbaf368599f0b77.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "bb8e1d6e01977c930622f21fedd6ab65c6382e8c42812011b12565838a71e43d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ce55b16f5c74e36009a336a4eaaedc68311f29b1eefcb1ad2328725791696029", "generation_seconds_batch": 26.328787826001644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03692145645618439, "target_z": -0.4121093670570575, "ce": 6.133810997009277, "genuineness": 4.507347106933594, "identity": 0.5517178177833557, "hypothesis": "J'ai trouvé la 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_Sourness/bb8e1d6e01977c930622f21fedd6ab65c6382e8c42812011b12565838a71e43d.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "bbbc911e36b38578cfe5486d753785e2eb37e492b8360ee3952b4b8b6bef78d7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "61d55b0bcfc267fde03985700239173d6fd52ba4ee5af4bdbbe20d4168190fb5", "generation_seconds_batch": 23.752512108068913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.133723735809326, "target_z": 4.437499797522279, "ce": 5.919358730316162, "genuineness": 3.6349775791168213, "identity": 0.3314676880836487, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/bbbc911e36b38578cfe5486d753785e2eb37e492b8360ee3952b4b8b6bef78d7.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "bbebd36b40b63a158650c7deef85d80894677830a90536a32e5bb2a883d7d262", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e3e0790740bb936687808ba42c65956ccca7820dc43989b68416c40fc26f8df0", "generation_seconds_batch": 22.951010779943317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 6.300607204437256, "genuineness": 4.293961524963379, "identity": 0.2856060266494751, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/bbebd36b40b63a158650c7deef85d80894677830a90536a32e5bb2a883d7d262.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "bc16b5c412a1718c591792037193207d3dd2ebe6fd9e95eaac0f2ba5f3dbb93a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "92cc44329d267c40971b970abd596d117e78302da6553cb7888f216a9ceb865b", "generation_seconds_batch": 27.127229621983133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24212603271007538, "target_z": 0.06249999569196339, "ce": 5.895530700683594, "genuineness": 3.6412534713745117, "identity": 0.4736874997615814, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/bc16b5c412a1718c591792037193207d3dd2ebe6fd9e95eaac0f2ba5f3dbb93a.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "bdbfd4b8e0c3ecbbe417e413f5de6dcad8ec2dfc97719e53a5123ac65fbbd92e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "82eb0ad8973ec094eadcc4937ff4d310755daf78dc8e9017fd4cf5139f2fa5ce", "generation_seconds_batch": 16.238349042949267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09687834978103638, "target_z": -0.2734374940764497, "ce": 6.09409761428833, "genuineness": 3.785602569580078, "identity": 0.363064169883728, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/bdbfd4b8e0c3ecbbe417e413f5de6dcad8ec2dfc97719e53a5123ac65fbbd92e.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "bdc3c34b196c45d148f040d43de97846ae8834b434d9b892afc1d8bdfed7fd7e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "89d9f32a84d7d4c404ca08e6ba1268635cbd9b3837a9f0c8f2de62b70ffca2c4", "generation_seconds_batch": 32.58281185606029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020876646041870117, "target_z": -0.4492187599623347, "ce": 6.260893821716309, "genuineness": 4.105680465698242, "identity": 0.5038152933120728, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/bdc3c34b196c45d148f040d43de97846ae8834b434d9b892afc1d8bdfed7fd7e.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": "bdc43924b658af5d1bf58f5ddc9adf4cb7c051df5bf5956d3a580c18335db3d3", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "896f9d0c96562a3c463aae6e6bfb572fb999c4fc9dc5bf8349e443ae9bfe0ee6", "generation_seconds_batch": 14.359492246992886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4751979112625122, "target_z": 0.6015625145396236, "ce": 6.078212261199951, "genuineness": 4.193545341491699, "identity": 0.7607654929161072, "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_Sourness/bdc43924b658af5d1bf58f5ddc9adf4cb7c051df5bf5956d3a580c18335db3d3.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": "be26462fcdb81f4e6ee07800977b2f891e6f4be967383d3af25a5846db68cbb7", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Your message arrived after I had left.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af69c3b63f77da7842ef5c5f4faf1a0f45ab3ecfb4bb00ebcde7ce90527413f4", "generation_seconds_batch": 24.959854287910275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4194633364677429, "target_z": 0.4726562712709308, "ce": 6.308549880981445, "genuineness": 4.061748504638672, "identity": 0.3830563426017761, "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_Sourness/be26462fcdb81f4e6ee07800977b2f891e6f4be967383d3af25a5846db68cbb7.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "bebe4489ad2493f9c4fe984b8a3be233d9d0c1167bbbab87bb392618c2eb552a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0df6c1ba596440b224536771ebd5cf9bdfe94d87fe7d5638eb8ef2e93bea2010", "generation_seconds_batch": 24.157243715017103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11038976162672043, "target_z": -0.24218749623046795, "ce": 6.149696350097656, "genuineness": 4.344170093536377, "identity": 0.5067039132118225, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/bebe4489ad2493f9c4fe984b8a3be233d9d0c1167bbbab87bb392618c2eb552a.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "bf3bc68ab72e4e01090029f8875a42f710329880b387b099f669e6a4672d4e71", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "68ee6b1c727fd7df472a301933de8622f9cce88e39da92b28d9d61d8149afa2c", "generation_seconds_batch": 24.154377440921962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0766112208366394, "target_z": -0.32031251669364186, "ce": 6.356205940246582, "genuineness": 4.400654315948486, "identity": 0.12432076781988144, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/bf3bc68ab72e4e01090029f8875a42f710329880b387b099f669e6a4672d4e71.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": "bfc2a2cdc28fefadacd7c054331fc8d278b6deacb487eb23256b63266cf79624", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b88528ba2a275b1b9ca6f086fa2aaddb9c8036c528183fec293327aa919edee7", "generation_seconds_batch": 15.44909840496257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8771624565124512, "target_z": 1.531250049542421, "ce": 6.181467056274414, "genuineness": 4.105680465698242, "identity": 0.43441516160964966, "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_Sourness/bfc2a2cdc28fefadacd7c054331fc8d278b6deacb487eb23256b63266cf79624.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "bfe1a3c7f1a81c55a2b9f4f77a14af476da16ab91c4ea4dfab38fc2ac22bc71b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "32dd9fc062d10ac5f0aa2ce112d13440d943c03313685b1185cb0b331b1a0683", "generation_seconds_batch": 26.015927143977024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0723889172077179, "target_z": -0.330078111941264, "ce": 6.062326908111572, "genuineness": 4.055472373962402, "identity": 0.6439374685287476, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/bfe1a3c7f1a81c55a2b9f4f77a14af476da16ab91c4ea4dfab38fc2ac22bc71b.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "c044f87a5037e4d2c5389fc6094af46a1bfc3791a6187a9af7aa45eb6464b6ea", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5675aa519212a677ab575c893bb50d3eb78fca68fe2d9c4a9aaf7d10af67e9d4", "generation_seconds_batch": 15.226851866929792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10954529792070389, "target_z": -0.24414062217285099, "ce": 6.1894097328186035, "genuineness": 4.607763767242432, "identity": 0.7549861669540405, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c044f87a5037e4d2c5389fc6094af46a1bfc3791a6187a9af7aa45eb6464b6ea.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "c049173efe8638ad3a8fa8708aa5671ae559806dcce3f9737c821219395ed4d9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8ca651155c7680b20b2e74861113e38e625be6d40bcab3da7ac3c4e8c9aa263a", "generation_seconds_batch": 16.666050552972592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03316900134086609, "target_z": -0.5742187513462614, "ce": 6.332377910614014, "genuineness": 4.356721878051758, "identity": 0.47993114590644836, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c049173efe8638ad3a8fa8708aa5671ae559806dcce3f9737c821219395ed4d9.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "c0b8d517380cc0965710d5c1f1e42c2a46eb282f59d2cc6c67bc9bba15446e93", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "478023ca63443dd45492fb47e1bb855d55b803ffafb4a0a31a4a22f9624184cd", "generation_seconds_batch": 17.218748182058334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21848106384277344, "target_z": 0.007812503769532035, "ce": 6.197352409362793, "genuineness": 4.331617832183838, "identity": 0.44054603576660156, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c0b8d517380cc0965710d5c1f1e42c2a46eb282f59d2cc6c67bc9bba15446e93.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": "c0cca4b2ca2c817d3a05ae09e49def03877929ed6f95e4ec19683875fde77bdb", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d738bd6d97666423d3f5d18185b3d5b39331b936bb18fe034bf8a3bff100ff7", "generation_seconds_batch": 15.400056248996407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1323457956314087, "target_z": -0.19140627342494906, "ce": 6.2767791748046875, "genuineness": 4.507347106933594, "identity": 0.6441550254821777, "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_Sourness/c0cca4b2ca2c817d3a05ae09e49def03877929ed6f95e4ec19683875fde77bdb.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "c0d23f3b61e6cba8cda6854863610171b0a1bee12e8f1df33846bd88a897915a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "045852c068ef2df0004b9741c4c211ea8d147a208bb6c58d899c3fb49e40ea8e", "generation_seconds_batch": 23.01965280494187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10194512456655502, "target_z": -0.26171875565429803, "ce": 6.133810997009277, "genuineness": 3.6287014484405518, "identity": 0.2870604991912842, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c0d23f3b61e6cba8cda6854863610171b0a1bee12e8f1df33846bd88a897915a.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "c0ff31ee5cfc17d98fbedbc4385cf43f2ce06059bc10cb5f345fc87b99081f25", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "75af018c4007ec157114b5abbdf37ac1b0b4256e2a0dad2bcdb8a3323a8bdc62", "generation_seconds_batch": 24.729894953081384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02594342827796936, "target_z": -0.4375000043080366, "ce": 5.895530700683594, "genuineness": 4.268857479095459, "identity": 0.551342248916626, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c0ff31ee5cfc17d98fbedbc4385cf43f2ce06059bc10cb5f345fc87b99081f25.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "c10a3ae5510d0c79cbac546b129212076540f83f7fcc7b9935c0769d4ca6c54e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a9ab341d07a3ff137190156427d51694aedc1d90268f08f4367b0d5cc9a23576", "generation_seconds_batch": 23.747901925002225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.028102219104766846, "target_z": -0.5624999956919634, "ce": 6.229123115539551, "genuineness": 4.319066047668457, "identity": 0.5216792821884155, "hypothesis": "I fOund the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c10a3ae5510d0c79cbac546b129212076540f83f7fcc7b9935c0769d4ca6c54e.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "c11aa8f45cda9a73c3434d0cc520061cedfaac34cf1e772340dc1ddda9bed4f7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e3ba21e0677d8e6d415daa417160798895c0ec80232fa426b19713124fc230b", "generation_seconds_batch": 17.79606260592118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48870933055877686, "target_z": 0.6328125296177517, "ce": 5.824047088623047, "genuineness": 4.193545341491699, "identity": 0.566673755645752, "hypothesis": "J'ai trouvé la 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_Sourness/c11aa8f45cda9a73c3434d0cc520061cedfaac34cf1e772340dc1ddda9bed4f7.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "c1a793b1b1f11089c44fb5c6e1ffe62198997bee795e53893291277a629a5eed", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d7f53b3e58cf39303fceb5b77f9c89d7acd3a0fd42f2c5e63ca2004ae4c6c4cb", "generation_seconds_batch": 23.940836893976666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05296625196933746, "target_z": -0.37500000861607324, "ce": 6.109982967376709, "genuineness": 4.394378662109375, "identity": 0.5853930711746216, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c1a793b1b1f11089c44fb5c6e1ffe62198997bee795e53893291277a629a5eed.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "c234e63619678401ce7b92636e2237e0b13e240eca0c66bcc8f47c3ca42f75f2", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8a593eb690537e3c4d33cca0ed9184079dfb5ec6bf4010664f62041812a11461", "generation_seconds_batch": 17.79606260592118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.259015291929245, "target_z": 0.10156248007533067, "ce": 6.1020402908325195, "genuineness": 4.319066047668457, "identity": 0.6715512275695801, "hypothesis": "J'ai trouvé la 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_Sourness/c234e63619678401ce7b92636e2237e0b13e240eca0c66bcc8f47c3ca42f75f2.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": "c26f24fcb65bacc50b3ff0c5378ed9012b0d9f10b32e2171e840d4b948d03d80", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "052f143a62ee867308d54f0a377b6568e0aac413f64ce6e413162b6ebab3f755", "generation_seconds_batch": 23.291984883951955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7015140652656555, "target_z": 1.1249999913839268, "ce": 6.054384231567383, "genuineness": 4.362998008728027, "identity": 0.7703909873962402, "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_Sourness/c26f24fcb65bacc50b3ff0c5378ed9012b0d9f10b32e2171e840d4b948d03d80.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "c3114ab143df7d272761a2f8548a447338075518a166dd61c9e2490ebcb460d3", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "588db387f6bf4c8c2624d046f97a3986ad0ffce97f6849bdb1c40ea16c16734c", "generation_seconds_batch": 22.478088643052615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2487263679504395, "target_z": 2.390625188476602, "ce": 5.935244083404541, "genuineness": 3.798154592514038, "identity": 0.5500590801239014, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c3114ab143df7d272761a2f8548a447338075518a166dd61c9e2490ebcb460d3.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "c32661a4dedbb18a24626ca2824d2c47c39dffc16a83930a0b2ad3bd47375fc1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6e458ad304851afba05e2bf0f2156d158b8f7f90d750e1962c84c99b798c2139", "generation_seconds_batch": 18.633595627034083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03861038386821747, "target_z": -0.40820311517229146, "ce": 6.157639026641846, "genuineness": 4.482243061065674, "identity": 0.44634270668029785, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c32661a4dedbb18a24626ca2824d2c47c39dffc16a83930a0b2ad3bd47375fc1.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "c35a74191834418c2d6b84af32610738ee8de0939290bd1cbcc6d1a39504da53", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fbcf06dc45b812eb065de71e38a4c6b89b18b89959c246986df117756df16dac", "generation_seconds_batch": 25.131208483944647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3856847882270813, "target_z": 0.39453123357561043, "ce": 6.070269584655762, "genuineness": 4.281409740447998, "identity": 0.44468000531196594, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c35a74191834418c2d6b84af32610738ee8de0939290bd1cbcc6d1a39504da53.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "551a8f29976f89de726b095b7c6e56d96de5afe0703bf3277afe8aba35f7d13d", "generation_seconds_batch": 18.526117490953766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.145012766122818, "target_z": -0.16210934982491104, "ce": 5.990842819213867, "genuineness": 4.545003414154053, "identity": 0.7692845463752747, "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_Sourness/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "c39b5072b018d161a370b163cb5a146be8095014f48521f438d58f940879a3b9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1886848845f04b82591ba061b18315f5be1b1d56fec4b3dd8348889cf2557666", "generation_seconds_batch": 21.982353833969682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3274168372154236, "target_z": 0.2597656469440615, "ce": 6.181467056274414, "genuineness": 4.143336772918701, "identity": 0.3742028474807739, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c39b5072b018d161a370b163cb5a146be8095014f48521f438d58f940879a3b9.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "c3d36c44bdba240bede7ba9a3f4d935d9b4e3a139a8f21dbeaf6e1bb71c71714", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d83b2658373257134c30ea74f4dd30e33fbfdaad3123795eb5e1d77d9a4b98ed", "generation_seconds_batch": 23.794633826008067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019187718629837036, "target_z": -0.4531250118471007, "ce": 6.173524379730225, "genuineness": 4.287685871124268, "identity": 0.4027876853942871, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c3d36c44bdba240bede7ba9a3f4d935d9b4e3a139a8f21dbeaf6e1bb71c71714.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "c41110ba0131a31f169de42827a14eb8aaa1a9535f4f4b755f030fd87fa63923", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "321f8ece445eff19e09e0489d7269687b603189f1b65d3e5ab485c87a6a637e4", "generation_seconds_batch": 23.89400055410806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6743357181549072, "target_z": 3.374999836294609, "ce": 5.839932441711426, "genuineness": 3.7416701316833496, "identity": 0.506439208984375, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c41110ba0131a31f169de42827a14eb8aaa1a9535f4f4b755f030fd87fa63923.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "c43057fb3892051c151321ee15528f67a9c81768d3a3b76c68dd66c8dcfe0135", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a0d0dd7cf1d4d38c74d342b84ffd915232f6e5c355d0884fc8808ad8c2fff5eb", "generation_seconds_batch": 23.09731155296322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029321283102035522, "target_z": -0.4296875005385046, "ce": 6.09409761428833, "genuineness": 4.507347106933594, "identity": 0.5867077708244324, "hypothesis": "J'ai trouvé la 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_Sourness/c43057fb3892051c151321ee15528f67a9c81768d3a3b76c68dd66c8dcfe0135.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": "c44acf54742a368726469d7238e66ef0adeba34521e7dc16eb7421f70bff7d56", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9c8ff617b4cabdce18419f848970df08bbb2f74681cd0839056d4c009625d7e0", "generation_seconds_batch": 18.39402201701887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04874393343925476, "target_z": -0.38476563832798827, "ce": 6.221180438995361, "genuineness": 4.243753433227539, "identity": 0.5641896724700928, "hypothesis": "Las llaves están en la mesa de la cocina. Mire en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c44acf54742a368726469d7238e66ef0adeba34521e7dc16eb7421f70bff7d56.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "447475ed9df5c6d0b6b0ac0ee54066484da92eb936513c5acf839e714ea7be9c", "generation_seconds_batch": 16.319907204946503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5157321691513062, "target_z": 0.695312559774008, "ce": 6.173524379730225, "genuineness": 4.306513786315918, "identity": 0.5439347624778748, "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_Sourness/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "c49bf3503738febacdbc84694323ded7ba0af7fc0915a9f0181eacb97ed0bb4f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ff0668d950e2a07f76aa934c5cd196d5d30ff91667cefe41e0d94d17b824d13f", "generation_seconds_batch": 22.631877562962472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0267878919839859, "target_z": -0.4355468783656536, "ce": 6.006728172302246, "genuineness": 4.319066047668457, "identity": 0.6782205104827881, "hypothesis": "J'ai trouvé la 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_Sourness/c49bf3503738febacdbc84694323ded7ba0af7fc0915a9f0181eacb97ed0bb4f.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "c4bf44d74d302a34facd702c4f9d0525e2309835eefdddec42cfb9a10fe630d5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "111de8f772d232a1b5634646ecbd40c144c7ac7daf2cadea8aeea56e95a43313", "generation_seconds_batch": 26.70786864904221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05296625196933746, "target_z": -0.37500000861607324, "ce": 5.752562999725342, "genuineness": 4.557555198669434, "identity": 0.5361133217811584, "hypothesis": "J'ai trouvé la 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_Sourness/c4bf44d74d302a34facd702c4f9d0525e2309835eefdddec42cfb9a10fe630d5.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": "c4c4fcfc41b609c16167991ae5e09bb2f3ed83c2862deb13f86fce5130facb2a", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65606b0a10faae3b8a84cf6a9202f7488d147b13fa8f326971aa06e8082fb67d", "generation_seconds_batch": 23.13393048790749, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008209705352783203, "target_z": -0.4785156146337869, "ce": 6.133810997009277, "genuineness": 4.3127899169921875, "identity": 0.5252125263214111, "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_Sourness/c4c4fcfc41b609c16167991ae5e09bb2f3ed83c2862deb13f86fce5130facb2a.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "c4c7341bda6274006c3d7e16552ddf04e0ebe5c7d1e536511e23d2ef2150b2aa", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "89298131b4255ca649daba1223dcf4c6d91cea91ebf9f83aa23aaef38bf166d8", "generation_seconds_batch": 18.085487248026766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6000230312347412, "target_z": 3.203125029079247, "ce": 6.006728172302246, "genuineness": 3.760498285293579, "identity": 0.5756226778030396, "hypothesis": "Ik heb het kleine dode 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_Sourness/c4c7341bda6274006c3d7e16552ddf04e0ebe5c7d1e536511e23d2ef2150b2aa.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "c56b57f677f32750b931d178d947949c5dd11b316229415d5b976f4af0a104d2", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fd5a104938d1047447626d8323de60d7a27bb183cc5530a148549e401824af11", "generation_seconds_batch": 23.62813285505399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009898632764816284, "target_z": -0.4746093627490209, "ce": 6.332377910614014, "genuineness": 4.607763767242432, "identity": 0.684662938117981, "hypothesis": "J'ai trouvé la 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_Sourness/c56b57f677f32750b931d178d947949c5dd11b316229415d5b976f4af0a104d2.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "c5f877dcc3eba3ceb62de3e5dca67b25f2e731fcad18977ab78ee70f494a5a4a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "eb1149f9a5c16383096ce50092fd6820f2e895d9e99ccf1b6d27c83ce19bb6e8", "generation_seconds_batch": 24.424193218001164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02425450086593628, "target_z": -0.4414062561928026, "ce": 6.356205940246582, "genuineness": 4.432034492492676, "identity": 0.5064652562141418, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c5f877dcc3eba3ceb62de3e5dca67b25f2e731fcad18977ab78ee70f494a5a4a.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": "c6f40dc45acb65ccd14ca76001323cfdce3a288eaa651ef1f3c31545d7211fa1", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "507bbdc29a8a447151cb04dd554d3b6802e73d6fe3ed1d01bd517a36ef4148eb", "generation_seconds_batch": 18.88043193600606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11967885494232178, "target_z": -0.2207031280964013, "ce": 6.109982967376709, "genuineness": 4.394378662109375, "identity": 0.786345362663269, "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_Sourness/c6f40dc45acb65ccd14ca76001323cfdce3a288eaa651ef1f3c31545d7211fa1.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "c75ba3f679dfbe4ceacced241340090f4dac9cc3e67b55c4abe8ae671eef074e", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4f4f3be08f6a68a1ac4d6cc5dcfa0470757abec2c468f1762e7aac8f0b3a718f", "generation_seconds_batch": 18.129369769943878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5630220770835876, "target_z": 0.8046874746902849, "ce": 5.796247482299805, "genuineness": 3.9299514293670654, "identity": 0.36780673265457153, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c75ba3f679dfbe4ceacced241340090f4dac9cc3e67b55c4abe8ae671eef074e.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": "c7f9d3d2d54ebd8541df8fad2473beb8d763075803f39327f0da94ba6de56e99", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2cd9470b361e507ee409dfba5eb116db2989ee2cf292de11ccc9368cb026f77", "generation_seconds_batch": 20.192119134007953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07407784461975098, "target_z": -0.326171860056498, "ce": 6.23706579208374, "genuineness": 4.425758361816406, "identity": 0.7338333129882812, "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_Sourness/c7f9d3d2d54ebd8541df8fad2473beb8d763075803f39327f0da94ba6de56e99.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "f7cf12df7284901761a562e992cb5742187d9f26d78711b324680150837af89d", "generation_seconds_batch": 17.284028002992272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14163491129875183, "target_z": -0.1699218535944431, "ce": 6.109982967376709, "genuineness": 4.425758361816406, "identity": 0.6772381067276001, "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_Sourness/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "c83cba4c369164d62c36875fff008738279f6c618fcedb35cf91fdb3596cbac0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "abd439014004c537d71f9a45bcbd8d520bf61de823a3e9eca48e84e608e0cd83", "generation_seconds_batch": 30.584541736985557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20834749937057495, "target_z": -0.01562500753906407, "ce": 5.9431867599487305, "genuineness": 4.005263805389404, "identity": 0.47880858182907104, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/c83cba4c369164d62c36875fff008738279f6c618fcedb35cf91fdb3596cbac0.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": "c84daf4b6ee7cb6b9e4375e489b77c8cc5b58347e4c1d1252a25e5bf5680c267", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Escribí el número en el sobre.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e92401f71ebe07373495a6fba6539a0d39abe31e51cbdc017a9789052ae5254e", "generation_seconds_batch": 22.45560171699617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07998907566070557, "target_z": -0.31250001292410984, "ce": 6.229123115539551, "genuineness": 4.419482707977295, "identity": 0.6526074409484863, "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_Sourness/c84daf4b6ee7cb6b9e4375e489b77c8cc5b58347e4c1d1252a25e5bf5680c267.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "fe24543453f7082a04b08c2476756760e68e5a31299a0719651e78421d43f99a", "generation_seconds_batch": 17.46446179994382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05972196161746979, "target_z": -0.35937500107700915, "ce": 6.395919322967529, "genuineness": 4.3127899169921875, "identity": 0.4016159176826477, "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_Sourness/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.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": "c94c9d908bbe6a2fdbe1cb05c0429fb0696883a452cbdf325b6220972462afe2", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14925a81a008c482f1e076274392f080f9f5218f1f056b8d8c61461340ac4985", "generation_seconds_batch": 15.426428108941764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06647767126560211, "target_z": -0.3437499935379451, "ce": 6.308549880981445, "genuineness": 4.256305694580078, "identity": 0.601409912109375, "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_Sourness/c94c9d908bbe6a2fdbe1cb05c0429fb0696883a452cbdf325b6220972462afe2.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "ca01a39729567573f84d633b5ceeb70be40417de5dcae97882be4b4e83dfb914", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "27ffb48a06818cb7e2bade1a435770c094990f19330b0eee4372b1d196f6c2c4", "generation_seconds_batch": 18.48414045199752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8433839082717896, "target_z": 1.4531250118471006, "ce": 6.165581703186035, "genuineness": 4.030367851257324, "identity": 0.6172077655792236, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ca01a39729567573f84d633b5ceeb70be40417de5dcae97882be4b4e83dfb914.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "ca2d9d9cb4778992f4dbe57532e599db78abd2101f35d948f438d9cb18acd619", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "65d06db18ae93a8b70b08f500c9068179f5ccd11440df8c750bf678c6ae16126", "generation_seconds_batch": 23.165557854925282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053810715675354004, "target_z": -0.37304688267369024, "ce": 6.117925643920898, "genuineness": 4.457139015197754, "identity": 0.7011948823928833, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ca2d9d9cb4778992f4dbe57532e599db78abd2101f35d948f438d9cb18acd619.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "ca6d54d516fee94b3be9a630f2e09236c9fef9b5fdd90a14ee16714764509990", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2257d18c5eeaa77e79646d6f26dc2d035d4af388880c5370f46d65db60cb8f89", "generation_seconds_batch": 25.22348839393817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16950219869613647, "target_z": -0.10546873196009669, "ce": 6.09409761428833, "genuineness": 4.419482707977295, "identity": 0.6041980385780334, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ca6d54d516fee94b3be9a630f2e09236c9fef9b5fdd90a14ee16714764509990.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "ca753d69208dd04ce9b65e43a6ed5c1515d96fbfd7494d5881d6c93c505a847a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1238e71ec98eb1b579214988b5b988c0162d8028bea9bede8a43b8804c08df3b", "generation_seconds_batch": 24.331450346042402, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0022984594106674194, "target_z": -0.492187496230468, "ce": 6.022613525390625, "genuineness": 4.143336772918701, "identity": 0.29297101497650146, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ca753d69208dd04ce9b65e43a6ed5c1515d96fbfd7494d5881d6c93c505a847a.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "cb5667269f64c9ef4e028f48b3b67055f4e2e163c6a5f16d8164e1874bf92320", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b0e121a2d80e30f89a075a8b549c25940a5f2a3a2ca813bf694403414e5ed7d6", "generation_seconds_batch": 21.860219744965434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23199248313903809, "target_z": 0.039062518847660176, "ce": 5.736677646636963, "genuineness": 4.256305694580078, "identity": 0.5646070241928101, "hypothesis": "J'ai trouvé la 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_Sourness/cb5667269f64c9ef4e028f48b3b67055f4e2e163c6a5f16d8164e1874bf92320.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "cba200063132e7e6ee90d9088420c3a995d240233b584efc6e774640b3b63e5d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "49ea9bbe89b719f3bfb09946821b63c89dbf87657e4a6f424665003363528d51", "generation_seconds_batch": 24.739379816921428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09856727719306946, "target_z": -0.2695312421916836, "ce": 6.149696350097656, "genuineness": 4.099404335021973, "identity": 0.3204441964626312, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/cba200063132e7e6ee90d9088420c3a995d240233b584efc6e774640b3b63e5d.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "cbf461b31066de356a17770280ba159315c1888fb7e097bc9229e9d47d4a9f3b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eba9d081fb1556b95349f72a252f441ca1728d101a90ea814860e19409700df6", "generation_seconds_batch": 23.385917713982053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3924404978752136, "target_z": 0.41015624111467447, "ce": 5.343515396118164, "genuineness": 3.5596652030944824, "identity": 0.4713420271873474, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/cbf461b31066de356a17770280ba159315c1888fb7e097bc9229e9d47d4a9f3b.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "cc6cd63c2eb968db909a88bd3c0462858e2fa7dedebab4a814e182f9ac1fec42", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1638fa513f4d2595a2146c08bb799e1007000be246a7dda1fdcfb2d11bbb22a2", "generation_seconds_batch": 23.56518282799516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04452162981033325, "target_z": -0.39453123357561043, "ce": 5.8875885009765625, "genuineness": 3.998987913131714, "identity": 0.43646275997161865, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/cc6cd63c2eb968db909a88bd3c0462858e2fa7dedebab4a814e182f9ac1fec42.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "cc95f64e1ae575e565ae4c456908df6fe028a91ed4e7b599d5221393305e4ec4", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34167c2c876e134d8b14f3aad9954d13c21c4580616c01d57a9a9f223834a959", "generation_seconds_batch": 24.678454273031093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04452162981033325, "target_z": -0.39453123357561043, "ce": 6.062326908111572, "genuineness": 4.18099308013916, "identity": 0.3918309211730957, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/cc95f64e1ae575e565ae4c456908df6fe028a91ed4e7b599d5221393305e4ec4.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": "cd7397605c959578f49df190e4dafbb164d582bafc6a01cf4971a582441fec59", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc58348f51ce6d19c0a13da9e3c61dae3f089f08baa953fbee38fcbe99c04f55", "generation_seconds_batch": 14.42911142797675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05887749791145325, "target_z": -0.36132812701939215, "ce": 5.990842819213867, "genuineness": 4.168440818786621, "identity": 0.5515443682670593, "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_Sourness/cd7397605c959578f49df190e4dafbb164d582bafc6a01cf4971a582441fec59.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": "cd78fa05108646a323bfd587b3e248a276195945070d4672b5207332e906a73b", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8705efceda2e61583236fdda5dbf8d83f8e8eb36b88808d264c7409809db517a", "generation_seconds_batch": 14.461816993076354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012432023882865906, "target_z": -0.46874998492187187, "ce": 5.967014789581299, "genuineness": 4.362998008728027, "identity": 0.8112532496452332, "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_Sourness/cd78fa05108646a323bfd587b3e248a276195945070d4672b5207332e906a73b.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "cdc69eb578a57a5153681d0b539a0ebc20db7edf645710a4d2a41d2deceb5b12", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c1aca07d536e4aac305a7db69651628f62216523a3290ecbe3772b624f61c929", "generation_seconds_batch": 17.843615421094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2691488564014435, "target_z": 0.12499999138392678, "ce": 5.621508598327637, "genuineness": 3.7918784618377686, "identity": 0.4556193947792053, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/cdc69eb578a57a5153681d0b539a0ebc20db7edf645710a4d2a41d2deceb5b12.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "cdecfbdce317f619a67bbdfdca62a3f29ec006beb7eaffcefccbcd40c5b0066f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "400360e66fc24f1bf02c2b966c0dafc2a81b44ce9134e52bc26076b21eda1ce3", "generation_seconds_batch": 22.488358848029748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5257103443145752, "target_z": 3.0312502218638855, "ce": 5.911416053771973, "genuineness": 4.20609712600708, "identity": 0.22268620133399963, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/cdecfbdce317f619a67bbdfdca62a3f29ec006beb7eaffcefccbcd40c5b0066f.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "ce3c6b67105ad91852d0f4a8eb63005570acfb681e1d0bcede29a6517dba5117", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bc6e547061b237912516c5933b80ebccc91158a3ffaf1f576e2dc6f07ceb0c7b", "generation_seconds_batch": 24.494850634015165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11883439123630524, "target_z": -0.22265625403878433, "ce": 6.1894097328186035, "genuineness": 4.400654315948486, "identity": 0.5461572408676147, "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_Sourness/ce3c6b67105ad91852d0f4a8eb63005570acfb681e1d0bcede29a6517dba5117.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "ce4491a7f919348bd0d2f3092bda108c7e98806618e3a18588925e7425b45ea5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c59dbdcc8c269c096356640d70ba121989495ddaa95813f20c3bdd4dbcb5c5aa", "generation_seconds_batch": 25.40885729098227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031010210514068604, "target_z": -0.42578124865373856, "ce": 6.356205940246582, "genuineness": 4.325342178344727, "identity": 0.42256882786750793, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ce4491a7f919348bd0d2f3092bda108c7e98806618e3a18588925e7425b45ea5.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": "ce5ff79258ecea58a130cf17c2a3c5d47f672c328d2a82ceb18fa2c2606b4485", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eae6638939205fa866afd869221b0b459132fd607d49f3b1b68dc3ecb17d7388", "generation_seconds_batch": 15.37391107599251, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03861038386821747, "target_z": -0.40820311517229146, "ce": 6.173524379730225, "genuineness": 4.262581825256348, "identity": 0.716444730758667, "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_Sourness/ce5ff79258ecea58a130cf17c2a3c5d47f672c328d2a82ceb18fa2c2606b4485.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "cf4da6801358fdc242b55b90b7af42d2f760ca0d02cc3ba16d5fe923a81515f1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d4f8ca669820f5a70c4a5dcc7e395580f191bc1391caf717f82b9e560aaea385", "generation_seconds_batch": 23.62813285505399, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02509896457195282, "target_z": -0.4394531302504196, "ce": 6.086154937744141, "genuineness": 4.65797233581543, "identity": 0.8379784822463989, "hypothesis": "J'ai trouvé la 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_Sourness/cf4da6801358fdc242b55b90b7af42d2f760ca0d02cc3ba16d5fe923a81515f1.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "9ea6e88827f85fc88c80b566b9bd0f1a4d7b58277d3ee797561f301258fa1adf", "generation_seconds_batch": 18.861882584984414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04283270239830017, "target_z": -0.39843748546037644, "ce": 6.24500846862793, "genuineness": 4.419482707977295, "identity": 0.5249724388122559, "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_Sourness/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "cffb5bffe8138728069c090f3b425d65b5bc8125dd14fc8986f2b7aecf891aeb", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "06bbe49a7a4a29624c670b36acd8802c0ec2b4d70ff52afccad6c3efc9d29524", "generation_seconds_batch": 24.955538467038423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08505585789680481, "target_z": -0.3007812572698118, "ce": 6.078212261199951, "genuineness": 4.262581825256348, "identity": 0.5535856485366821, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/cffb5bffe8138728069c090f3b425d65b5bc8125dd14fc8986f2b7aecf891aeb.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "d0482d6bbe910fcc1b0c9481c242dfac51d81606eadf84ee6499cd91dc960988", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "86b4f8153bb7a5d2a02c8e536bf74e6c2d6f1a85d187b9f6938d7cf32cdf626a", "generation_seconds_batch": 24.142467778059654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06056642532348633, "target_z": -0.35742187513462614, "ce": 5.998785495758057, "genuineness": 4.13078498840332, "identity": 0.4143897593021393, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d0482d6bbe910fcc1b0c9481c242dfac51d81606eadf84ee6499cd91dc960988.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "d048e9e3768829db9ced7648b9272328c6b71f817727f92d6e7ae91625f21cd1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fd0fcf8fef1adf56da8637bc7b1b5ee92b4318e09ac0e45d19328afda943d2ab", "generation_seconds_batch": 24.877978409989737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06141088902950287, "target_z": -0.35546874919224314, "ce": 6.149696350097656, "genuineness": 4.193545341491699, "identity": 0.3392487168312073, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d048e9e3768829db9ced7648b9272328c6b71f817727f92d6e7ae91625f21cd1.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "d08dbe6620307385cef07e8bcac59e4db970d787e72ff06eb03597ab73be705a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "64adcc6472681177cd05cfbc4d3a6a3de32c5d348a91be513fe4c830d76c2139", "generation_seconds_batch": 24.307108124019578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01965758204460144, "target_z": -0.5429687362681334, "ce": 6.213237762451172, "genuineness": 4.457139015197754, "identity": 0.7578156590461731, "hypothesis": "J'ai trouvé la 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_Sourness/d08dbe6620307385cef07e8bcac59e4db970d787e72ff06eb03597ab73be705a.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "d0a6103720c8564679809110c7b0f493af1e13b9246a12cf8834355f594080a8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "588ef8b1dfcbc2aca76723aecb6b52b4ae14d1e0125bf29d0c1705a2cfc0b3c7", "generation_seconds_batch": 21.511059255921282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7015140652656555, "target_z": 1.1249999913839268, "ce": 5.510311126708984, "genuineness": 3.289795398712158, "identity": 0.27827906608581543, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d0a6103720c8564679809110c7b0f493af1e13b9246a12cf8834355f594080a8.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": "d0db01fb787d8a735774c7afc65e6dbf2755adb863a94ada61d96b953a43ae5e", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The road turns left behind the bridge.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e6c195286e64d83eb93f85a3f61d3e76ecd455558ba65546e98a305cb124e0c", "generation_seconds_batch": 20.396762116928585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11292315274477005, "target_z": -0.23632811840331894, "ce": 6.419747352600098, "genuineness": 3.9927117824554443, "identity": 0.09019656479358673, "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_Sourness/d0db01fb787d8a735774c7afc65e6dbf2755adb863a94ada61d96b953a43ae5e.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "d0f120d291ff9087a1a7616787c388505b64370c02ae09778d148acf61211190", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6db7684db7dadf8250abed079d05a83281eecf518b55ecf4491e36cb2972a15c", "generation_seconds_batch": 17.190000729984604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10701190680265427, "target_z": -0.25, "ce": 6.022613525390625, "genuineness": 4.293961524963379, "identity": 0.3319881856441498, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d0f120d291ff9087a1a7616787c388505b64370c02ae09778d148acf61211190.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": "d0f60588789f98550441d75c202d0142cb3769e91d9a590e19c20c7b868ccc62", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "497ac06808035b4ec6bf7d242c68a305177f4f43d536fb276b68dbe27c04535b", "generation_seconds_batch": 23.9468159340322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008209705352783203, "target_z": -0.4785156146337869, "ce": 6.221180438995361, "genuineness": 3.8922953605651855, "identity": 0.17923542857170105, "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_Sourness/d0f60588789f98550441d75c202d0142cb3769e91d9a590e19c20c7b868ccc62.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "fe1c17b75649cc3ec7ed58553816c8873955ab7c6b9121b74818860ee52efa4f", "generation_seconds_batch": 19.354454244021326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06394428014755249, "target_z": -0.3496093713650941, "ce": 6.4515180587768555, "genuineness": 4.162164688110352, "identity": 0.5912209749221802, "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_Sourness/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "d12bcbb08fc03be7651ad050bdc508d058ae025fba4b61a38566d667c73c8ed2", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e622c04dfe0f57bfd476d5b9560c66d891c7026b5d826ecb126844055b61f4f0", "generation_seconds_batch": 19.36871140799485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2657710015773773, "target_z": 0.11718748761439474, "ce": 5.903473377227783, "genuineness": 3.9173994064331055, "identity": -0.09410829842090607, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d12bcbb08fc03be7651ad050bdc508d058ae025fba4b61a38566d667c73c8ed2.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": "d16885db47043de10a9de8e7c2d3b0d038908907ae6dbcfc01e0bbf225c32f79", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "620522703b09df8187c9479316002511d2e05723c9811a8d71c03e4788429692", "generation_seconds_batch": 22.423677165992558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14416828751564026, "target_z": -0.16406251023158694, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.7224342823028564, "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_Sourness/d16885db47043de10a9de8e7c2d3b0d038908907ae6dbcfc01e0bbf225c32f79.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "d1b26f3c5a4b1a5e5426466d134fe315afa4b81946dd3b0ac6e3105b826b4eab", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a9fcfc5919cfbf3e92fe27e6fcbeee8a110412037470f020dd782f8c436a42e9", "generation_seconds_batch": 17.566216173931025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13741257786750793, "target_z": -0.17968751777065103, "ce": 6.125868320465088, "genuineness": 4.293961524963379, "identity": 0.055534496903419495, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d1b26f3c5a4b1a5e5426466d134fe315afa4b81946dd3b0ac6e3105b826b4eab.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "d1d32007c85850bc8edddb7ab4466b2539f8efb7a8e2159b15117e9777d38c1c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d8bcaacd892553451f9fd6bc7c896095adf7d664c3d5097cfe503f58ddbc8a47", "generation_seconds_batch": 16.977350000990555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0010793954133987427, "target_z": -0.5, "ce": 5.998785495758057, "genuineness": 4.3127899169921875, "identity": 0.6548078656196594, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d1d32007c85850bc8edddb7ab4466b2539f8efb7a8e2159b15117e9777d38c1c.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "fe0dd83d70806f2cc4f88b5ce80fceead0828f5efc716e6d734fa34936239043", "generation_seconds_batch": 18.040136993979104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02509896457195282, "target_z": -0.4394531302504196, "ce": 6.38797664642334, "genuineness": 4.356721878051758, "identity": 0.6201208233833313, "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_Sourness/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "d2ae5bd310f71ad86772f5c5e8b4ead3d15e760ab9b614b7ed9d5643c421cea8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1531d3eae0715f22e430a89b43aaeb745f9f905efcdd757b845f4ec0a2315d03", "generation_seconds_batch": 30.584541736985557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1306568682193756, "target_z": -0.1953125253097151, "ce": 6.133810997009277, "genuineness": 4.049196243286133, "identity": 0.6326781511306763, "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_Sourness/d2ae5bd310f71ad86772f5c5e8b4ead3d15e760ab9b614b7ed9d5643c421cea8.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "d325246f21ed351ab15dbf7199855e0dc884d7235f260de977277dd08e853269", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7982d71026dc8fd3446ec574cfa46789b11e5b34860400f7157ad94fbbfe6568", "generation_seconds_batch": 26.7371344990097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00314292311668396, "target_z": -0.490234370288085, "ce": 6.260893821716309, "genuineness": 4.375550270080566, "identity": 0.46845439076423645, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d325246f21ed351ab15dbf7199855e0dc884d7235f260de977277dd08e853269.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "d35fce3393f65c7d236b67b629dca43eb8c5c714229a81e90ebb5b2b2e5f1b0c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5ecd66d0a362f0e4a2965a136936680046ff5ca092bcc94d361d9c1159ff9636", "generation_seconds_batch": 24.678454273031093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03945484757423401, "target_z": -0.40624998922990846, "ce": 6.229123115539551, "genuineness": 4.049196243286133, "identity": 0.4174724817276001, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d35fce3393f65c7d236b67b629dca43eb8c5c714229a81e90ebb5b2b2e5f1b0c.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": "d3f9865473dd4a79ac8a38297dcfb18a76e3efb9318d0f89d7748157e2173e0a", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4894f13b3eb617854f2b397bf06ee660330cb01d7d47ce9c2d3c54b5897d0a11", "generation_seconds_batch": 24.589789233054034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04789946973323822, "target_z": -0.3867187642703713, "ce": 5.903473377227783, "genuineness": 4.218649387359619, "identity": 0.6681751608848572, "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_Sourness/d3f9865473dd4a79ac8a38297dcfb18a76e3efb9318d0f89d7748157e2173e0a.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "f9524ef4b50f97111bc59102dcac01327ea142bc1590c1dd5181cbfe3f087e8f", "generation_seconds_batch": 17.673414538032375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031010210514068604, "target_z": -0.42578124865373856, "ce": 6.09409761428833, "genuineness": 4.381826400756836, "identity": 0.6499263644218445, "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_Sourness/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "d4c180034353c6d7c68e103e31804b53f82156f73c74b559a03f52f1723bf598", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "278971cfa09c89ff88cfad906aa9d47efc7db28cd71516db32d40f2dc71a9777", "generation_seconds_batch": 17.440542632015422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6878471374511719, "target_z": 3.406249851372737, "ce": 5.617537498474121, "genuineness": 3.653805732727051, "identity": 0.13983683288097382, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d4c180034353c6d7c68e103e31804b53f82156f73c74b559a03f52f1723bf598.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "d52da32308e1f0b75865e5bc0d3c611d06423989b7cdd5b174513d5a7182e344", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "43385db31ec4b47011771511fcd93390d997f8212dd0af23bdf702ff60b07aa4", "generation_seconds_batch": 16.322845098911785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0951894223690033, "target_z": -0.2773437459612157, "ce": 6.078212261199951, "genuineness": 4.306513786315918, "identity": 0.51486736536026, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d52da32308e1f0b75865e5bc0d3c611d06423989b7cdd5b174513d5a7182e344.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "d5a40deb3cb456ab49f843035e1d7d13f8b8fe47d6034d04a4ad0452ed3980e0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "36ed6c803b27749da2064fc8ad490e37ffaddac2f2574791199e8fd7c6492fe8", "generation_seconds_batch": 23.030938738025725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.026413291692733765, "target_z": -0.5585937438071974, "ce": 6.332377910614014, "genuineness": 3.9550557136535645, "identity": 0.5735131502151489, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d5a40deb3cb456ab49f843035e1d7d13f8b8fe47d6034d04a4ad0452ed3980e0.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "d74f91be798c6c175b0c974f031b59850cc3002e45c65b8da7eda412e0c7bfb2", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3d4b4740363d9445af066b8211a07aab025c7cdfa6d62e8d757a6ae587825381", "generation_seconds_batch": 24.955538467038423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6272013187408447, "target_z": 0.9531250463113936, "ce": 6.23706579208374, "genuineness": 4.231201171875, "identity": 0.37582939863204956, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d74f91be798c6c175b0c974f031b59850cc3002e45c65b8da7eda412e0c7bfb2.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "d75a0933b771f14d2cb816096c12f165ffd5f911709983cdb656f4d5e550bc29", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "702e0ea1f89c345faf385a0c92e5f2f3170afb7217061fd24e601cd8611db878", "generation_seconds_batch": 23.403234907076694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0056763142347335815, "target_z": -0.4843749924609359, "ce": 5.871703147888184, "genuineness": 4.143336772918701, "identity": 0.4315859079360962, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d75a0933b771f14d2cb816096c12f165ffd5f911709983cdb656f4d5e550bc29.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "d76908250c094153994d6a8b1f4648d0b6d6ce1e553d292df9bca4148276f0a5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71174f01c8c077fc40f7558d3265c672eaf35ec0262f03432a37ba8a18d2ec8a", "generation_seconds_batch": 22.688849003985524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14585721492767334, "target_z": -0.16015625834682093, "ce": 5.879645347595215, "genuineness": 4.049196243286133, "identity": 0.3394959568977356, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d76908250c094153994d6a8b1f4648d0b6d6ce1e553d292df9bca4148276f0a5.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "d79191f4180851e4f29208124e240132d2da14d159952e66b1710e8cbb78e5db", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3f52e5e3d16403d8b5854f67caeeaba55b6008b6894a9d7f2189bf0c760a321f", "generation_seconds_batch": 23.99027109402232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08505585789680481, "target_z": -0.3007812572698118, "ce": 5.847874641418457, "genuineness": 3.9676074981689453, "identity": 0.4662488102912903, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d79191f4180851e4f29208124e240132d2da14d159952e66b1710e8cbb78e5db.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "d81d36ca75c0eddb3ab4de7d507063a594524a2b06905794ece4823e0e274953", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c46fd97cbe45faf1850ac7d74556c6e5e98c82db3dc7cf2a8a65da8d2d511aba", "generation_seconds_batch": 20.788735862006433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13741257786750793, "target_z": -0.17968751777065103, "ce": 5.752562999725342, "genuineness": 4.118232727050781, "identity": 0.6423932313919067, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d81d36ca75c0eddb3ab4de7d507063a594524a2b06905794ece4823e0e274953.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": "d84447660e7418de1975f10fc987cde15bd826c3a88a6478a299ae808685801d", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Your message arrived after I had left.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "483ae7416029b408a8ecd9a0210f3cb70ed2c7a948ec62dc894d85cccab2826e", "generation_seconds_batch": 24.959854287910275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12896795570850372, "target_z": -0.19921874273018822, "ce": 6.356205940246582, "genuineness": 4.068024158477783, "identity": 0.3270682692527771, "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_Sourness/d84447660e7418de1975f10fc987cde15bd826c3a88a6478a299ae808685801d.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "d874f00929187682ad8bf242b323b8cdccb40a5acfb11f562283e419f65f209c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3944a9e43876f2b72f14826ff37ee9d27a04a0c656516b2856beba0c25e4d916", "generation_seconds_batch": 23.99044441699516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03861038386821747, "target_z": -0.40820311517229146, "ce": 6.062326908111572, "genuineness": 4.582659721374512, "identity": 0.48391634225845337, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d874f00929187682ad8bf242b323b8cdccb40a5acfb11f562283e419f65f209c.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "d8759597a1d3269bd5c81500898bc0da7cd8a041172a755709576295dd34f8f2", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "95352a0dc71b289fc5936961e448ffe05702617303980f0f71f3caa4ae3319ac", "generation_seconds_batch": 26.25428144505713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05296625196933746, "target_z": -0.37500000861607324, "ce": 6.197352409362793, "genuineness": 4.256305694580078, "identity": 0.6598578691482544, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d8759597a1d3269bd5c81500898bc0da7cd8a041172a755709576295dd34f8f2.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "d87d073b3b5a7c8849115fb40785a93b033e9cc2020ee6d84f8a4ba107fc8575", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "97bc474a4a4df72345a9ce83a8c1036ba214a0e1b61b10e901c6c8caaccdee3e", "generation_seconds_batch": 21.894793803920038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07745568454265594, "target_z": -0.31835939075125885, "ce": 5.998785495758057, "genuineness": 4.369274139404297, "identity": 0.5547792911529541, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d87d073b3b5a7c8849115fb40785a93b033e9cc2020ee6d84f8a4ba107fc8575.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "d8d4c14be65e4904377851be770003be3ed6e418af28670ca8d65b8fa170f4b5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bf11cfe7ee1b46db400c3690c6571ef5acd1ab27a6de6c0149edb1d32df08f13", "generation_seconds_batch": 21.440842052921653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014120951294898987, "target_z": -0.46484373303710586, "ce": 6.229123115539551, "genuineness": 4.413206577301025, "identity": 0.6293014883995056, "hypothesis": "Die Tür ist noch offen? Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d8d4c14be65e4904377851be770003be3ed6e418af28670ca8d65b8fa170f4b5.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "d9711c471f2e09d3a874042ce52594acc9af50d0f946bb6803bb45601db85cf3", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3a28e89550f6f9c3a0911d44255f3dc88efebc1b6eb582a56bacbf73031c76e9", "generation_seconds_batch": 25.14225311006885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02763235569000244, "target_z": -0.4335937524232706, "ce": 6.157639026641846, "genuineness": 4.632867813110352, "identity": 0.481931209564209, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d9711c471f2e09d3a874042ce52594acc9af50d0f946bb6803bb45601db85cf3.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "d98af359cc52b8e5af5d4eaa011c606e193371140ac5c29ee1c189e98f448ad7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e9f805341690767e5815ec4ad08b7790784d14a409330e32330358311c7328e2", "generation_seconds_batch": 22.951010779943317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04789946973323822, "target_z": -0.3867187642703713, "ce": 6.308549880981445, "genuineness": 4.3881025314331055, "identity": 0.2689882516860962, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d98af359cc52b8e5af5d4eaa011c606e193371140ac5c29ee1c189e98f448ad7.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "d9cff7b61701444a931e3f789cd20b3b9a553dc9f3ecf2a5a34f5c75718cca6a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d5760536e2080fd80637f711c91851363c2d1b11743c3502df4d36b606aedda9", "generation_seconds_batch": 17.39045716205146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07492230832576752, "target_z": -0.324218734114115, "ce": 6.213237762451172, "genuineness": 3.9425034523010254, "identity": 0.24790850281715393, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d9cff7b61701444a931e3f789cd20b3b9a553dc9f3ecf2a5a34f5c75718cca6a.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "d9db3e41f53f9b908c739c0f9f905dbee0d371a0157d0bc27943ccef965aaf11", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7769a0084720956bc42ad9684b92fcbb3d9807a0be05a620cfcf4fb2587d85c5", "generation_seconds_batch": 23.547983691096306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011212959885597229, "target_z": -0.5234375113085961, "ce": 6.165581703186035, "genuineness": 4.457139015197754, "identity": 0.34398502111434937, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/d9db3e41f53f9b908c739c0f9f905dbee0d371a0157d0bc27943ccef965aaf11.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": "d9fb8a2f610efba42f8a9f73396364dced2f8d53965b08b4611b7b5fc7649020", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "86b0d2990a195ced774f2fd80274837eda1efe18e55eacc54e19a29207e636a7", "generation_seconds_batch": 15.520973699982278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055499643087387085, "target_z": -0.3691406307889242, "ce": 6.252951145172119, "genuineness": 4.105680465698242, "identity": 0.442632257938385, "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_Sourness/d9fb8a2f610efba42f8a9f73396364dced2f8d53965b08b4611b7b5fc7649020.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d30d93b39f71f326d7b0434e36275c37951bc2e49b0920fa5b2775415134e32", "generation_seconds_batch": 15.371118218055926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12559010088443756, "target_z": -0.20703124649972024, "ce": 6.403861999511719, "genuineness": 4.105680465698242, "identity": 0.3606990873813629, "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_Sourness/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "db8c742f7f1e79e9fb0366e7e303a735a831d862b28b2e863395f159fdfb0e20", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f79460a1334000b7f420954c83987cf6f612f9cf362b9fb49df7b0f6915e5d95", "generation_seconds_batch": 19.926758044981398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48195362091064453, "target_z": 0.6171875220786877, "ce": 5.95112943649292, "genuineness": 3.660081624984741, "identity": 0.5710949897766113, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/db8c742f7f1e79e9fb0366e7e303a735a831d862b28b2e863395f159fdfb0e20.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "db90d43d7412023e98068a8b1dce0e37777415296b1e3c0880fe40075f6e76ae", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "43c457b35ebaed5a435a118a1e73e08cd34312b993162df98c5076b6f79bdbfc", "generation_seconds_batch": 22.392845108988695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40510743856430054, "target_z": 0.43945309578612674, "ce": 5.550024509429932, "genuineness": 3.6789097785949707, "identity": 0.39887991547584534, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/db90d43d7412023e98068a8b1dce0e37777415296b1e3c0880fe40075f6e76ae.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "dc34df816a38184ea1d025f9861674d68d921db61e602ed366ba73fce5c715cc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "56109cd39f851df665fed721c61516f9160506a2419e4bd539784ec3c6f3b347", "generation_seconds_batch": 22.39377275807783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020876646041870117, "target_z": -0.4492187599623347, "ce": 6.165581703186035, "genuineness": 4.111956596374512, "identity": 0.2724171280860901, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/dc34df816a38184ea1d025f9861674d68d921db61e602ed366ba73fce5c715cc.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "dc351392a7c2397858eb59b313dd3c87262a63710c422ee410de42783925b92d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d92e5e1e7697095c8a787ab63d4908e9284aea9b125a4c0200f16377aea93bcc", "generation_seconds_batch": 22.80610141309444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0723889172077179, "target_z": -0.330078111941264, "ce": 6.149696350097656, "genuineness": 4.432034492492676, "identity": 0.49293187260627747, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/dc351392a7c2397858eb59b313dd3c87262a63710c422ee410de42783925b92d.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "dc4efe76142110cc7a37412a8f5a9889cc82f804b0eafeb0c5cdb15d786a8b2b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b4d9f66378431b43b50e6ceed9b790a711e6e271577cb5b99e73f66aa081290f", "generation_seconds_batch": 26.7371344990097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006520777940750122, "target_z": -0.4824218665185529, "ce": 6.3641486167907715, "genuineness": 4.482243061065674, "identity": 0.5330032110214233, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/dc4efe76142110cc7a37412a8f5a9889cc82f804b0eafeb0c5cdb15d786a8b2b.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "dc5d32034a7574a5ad769ea33533a8febe18f61153c70e7db1d22e851fae9232", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "78dc4538dd366faf115cf0ccd1aa5b9ca1b43884bb17b1993f35bf76682ea1e3", "generation_seconds_batch": 24.111863664002158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04789946973323822, "target_z": -0.3867187642703713, "ce": 6.149696350097656, "genuineness": 3.785602569580078, "identity": 0.3336065411567688, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/dc5d32034a7574a5ad769ea33533a8febe18f61153c70e7db1d22e851fae9232.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "dc77b0c0c6008b2b8693ac41648362b1b42905f2e1f8c156b05142ff3a539dfd", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "63a092e46bd07a26ebc5b968c1271e7b259b4adbce7146560600e86772fd51c0", "generation_seconds_batch": 26.529815627960488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4243745803833008, "target_z": 2.7968748330635815, "ce": 5.831989288330078, "genuineness": 3.672633647918701, "identity": 0.5455513000488281, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/dc77b0c0c6008b2b8693ac41648362b1b42905f2e1f8c156b05142ff3a539dfd.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "dc849dae53c73bf13d814c1d5b7dc67952d0444ad90e4ee182fbf64eb0cfbc64", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9afc81bb21a4837fb8e2d9df7a663ee44c9c1b84ef4602bd00b17f0414fd1642", "generation_seconds_batch": 23.49852873501368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021721109747886658, "target_z": -0.4472656340199517, "ce": 6.372091293334961, "genuineness": 4.193545341491699, "identity": 0.533622145652771, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/dc849dae53c73bf13d814c1d5b7dc67952d0444ad90e4ee182fbf64eb0cfbc64.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "dd47c9d277abe0b8c26f739de85afa290d94d04df055efddf0ccc95c9c752798", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "84ddea9893263b6244c5c44a0c4364fe97ba14bdbde4542c72e044c29205d1bd", "generation_seconds_batch": 25.322767712990753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20159178972244263, "target_z": -0.03125001507812814, "ce": 6.09409761428833, "genuineness": 4.2249250411987305, "identity": 0.53075110912323, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/dd47c9d277abe0b8c26f739de85afa290d94d04df055efddf0ccc95c9c752798.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "dda6d3d460a3b4f42c49ac2626083a6eb9f4fc35e2c5e1f4d2734a05132681b7", "bucket": "emo_Sourness", "phase": "wording", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fdc4532e5a98a5a95990f2e25e1a7dd408a9aab374e4a42eb0a71d9b8af6c3ec", "generation_seconds_batch": 15.337394253001548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014965400099754333, "target_z": -0.4628906415590157, "ce": 6.205295085906982, "genuineness": 4.325342178344727, "identity": 0.6654166579246521, "hypothesis": "J'ai trouvé la 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_Sourness/dda6d3d460a3b4f42c49ac2626083a6eb9f4fc35e2c5e1f4d2734a05132681b7.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "ddc4c2c48f107322ff2bf15398c46b517f7e13d7022213214554a5da29ef8d08", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3e7942414b190b890a3f544efec4bc88ce6598ad4863829bd730015052c70f02", "generation_seconds_batch": 16.977350000990555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07914461195468903, "target_z": -0.31445313886649284, "ce": 6.09409761428833, "genuineness": 4.243753433227539, "identity": 0.7057497501373291, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ddc4c2c48f107322ff2bf15398c46b517f7e13d7022213214554a5da29ef8d08.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "dde8cabe42bd023fa9504b1feb8ff8976fe698eac92240d129562d8811298c36", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "91bb803a908fbdc68cf77ffb992a55592ae759b538d41bafbe4586f3714942f4", "generation_seconds_batch": 22.81100848002825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2892606258392334, "target_z": 2.484375233710986, "ce": 5.839932441711426, "genuineness": 3.537698984146118, "identity": 0.2760871648788452, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen!", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/dde8cabe42bd023fa9504b1feb8ff8976fe698eac92240d129562d8811298c36.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": "ddf0351e08ad5b22f72f0aebfebbe7ab6de56148f2ce392d689d997c30a1447d", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a8e75f13f669edd56b54311448a414259b44feb200e216d137930b6a05a6998b", "generation_seconds_batch": 20.60470909101423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1990584135055542, "target_z": -0.03710935844098427, "ce": 6.109982967376709, "genuineness": 4.13078498840332, "identity": 0.7343957424163818, "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_Sourness/ddf0351e08ad5b22f72f0aebfebbe7ab6de56148f2ce392d689d997c30a1447d.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "de0c2744bb961e59b552a87cfe74db655ba041ad6c5fbc714608e7c03c296aa0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "748f0688a12e09ec3553fb610eb2663f0e27cf020c720293c1a6aef17be7a3e2", "generation_seconds_batch": 23.803256203071214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9176966547966003, "target_z": 1.6249999569196338, "ce": 6.125868320465088, "genuineness": 4.281409740447998, "identity": 0.7226276397705078, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/de0c2744bb961e59b552a87cfe74db655ba041ad6c5fbc714608e7c03c296aa0.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "de462eacced0c1d4f29cacbe96c35460ee216653000636fa162212d097d33f59", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "84280024b300b4264d51de35cbbabb8044c0664751a057b205a3a3457c86bff7", "generation_seconds_batch": 22.571571714943275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0808335393667221, "target_z": -0.31054688698172683, "ce": 5.831989288330078, "genuineness": 3.9801597595214844, "identity": 0.536065399646759, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/de462eacced0c1d4f29cacbe96c35460ee216653000636fa162212d097d33f59.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "df2eef8c7ffee6c2484c252cefe32f2e8ffcf70543c6ad5b170d67f871b32c54", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "55a456e74df160e5913cf609315ff6f7f9a01867b417e1dbac4c71b72aadbf07", "generation_seconds_batch": 23.50296717695892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09012264013290405, "target_z": -0.2890625016155137, "ce": 5.919358730316162, "genuineness": 4.093128204345703, "identity": 0.5022444128990173, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/df2eef8c7ffee6c2484c252cefe32f2e8ffcf70543c6ad5b170d67f871b32c54.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": "df73befa08203d7ba39df5c5c7a969ade10121e0c657f2d64ec326790e652b4f", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e8c4f5daf3a1816fbee512aed80ded9c182654aeeb52e0c17f38e09442fb2ef", "generation_seconds_batch": 17.196808891021647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13825705647468567, "target_z": -0.1777343573639751, "ce": 6.141753673553467, "genuineness": 4.231201171875, "identity": 0.6139378547668457, "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_Sourness/df73befa08203d7ba39df5c5c7a969ade10121e0c657f2d64ec326790e652b4f.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "dfd9dd432e61b3075bb3c453ecabbf4e734a745a02338012b21533f8c92b754c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b4f7ff6f2384ba505d512a410a8116f695c6c59822540cc07ef626a3253fcdd6", "generation_seconds_batch": 26.791540961014107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02341003715991974, "target_z": -0.44335938213518566, "ce": 6.0146708488464355, "genuineness": 4.337893962860107, "identity": 0.48530709743499756, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/dfd9dd432e61b3075bb3c453ecabbf4e734a745a02338012b21533f8c92b754c.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "dff64a8e7afa67077595cb3ce577cee1ee19bf0f400ec3b18dda8a29f73a439b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "458deb63b989b35fe5dbf39bfb1ce4ac62829e7fcc1d5a1fe7828bd7cd86add4", "generation_seconds_batch": 15.747760157100856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06309981644153595, "target_z": -0.35156249730747713, "ce": 5.911416053771973, "genuineness": 3.7793264389038086, "identity": 0.19972826540470123, "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_Sourness/dff64a8e7afa67077595cb3ce577cee1ee19bf0f400ec3b18dda8a29f73a439b.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "e03b04b1caa1cf98044642b1a4f90311e4db6497efe0462ba987f6db0ae53f52", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "92e0aeaf4c5ca1bd1268d9531a32eb5899f97c4c1e2163475e6b936a442f4cb2", "generation_seconds_batch": 22.631877562962472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07154445350170135, "target_z": -0.332031237883647, "ce": 5.422942161560059, "genuineness": 4.13078498840332, "identity": 0.41051578521728516, "hypothesis": "J'ai trouvé la 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_Sourness/e03b04b1caa1cf98044642b1a4f90311e4db6497efe0462ba987f6db0ae53f52.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "e056dd22fb4c51529fd40859e2d33ba0f31ba8fe3e4194b0a42a9cc07384f2a0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "86c45122c7139c8aa1bfb1ab6018cd93f5d09b639090fcf2f1018b5f68b0c5a4", "generation_seconds_batch": 24.87057866191026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2217035293579102, "target_z": 2.3281251583203453, "ce": 5.935244083404541, "genuineness": 4.149612903594971, "identity": 0.3985857665538788, "hypothesis": "La puerta sigue abierta y 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_Sourness/e056dd22fb4c51529fd40859e2d33ba0f31ba8fe3e4194b0a42a9cc07384f2a0.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "e0c772c9a61cd8fff28fb5f1c9da32a44a838d26ca7c1ce94becf2507758eab6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ffea9c88a3339aeea534d203fd71391cfa80057ec16d26157b95d28a6cdf1755", "generation_seconds_batch": 22.693542191991583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17794682085514069, "target_z": -0.0859375070005595, "ce": 6.006728172302246, "genuineness": 3.936227321624756, "identity": 0.4245002865791321, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e0c772c9a61cd8fff28fb5f1c9da32a44a838d26ca7c1ce94becf2507758eab6.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": "e0cfdca4962d0aa9f89626cf7025af92b7627fd111edf70024f15d416676c781", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fce8602335029dc7386cdffc381e983bc4f6fe9b13c5a0a270cbb7bd8178c29a", "generation_seconds_batch": 15.473287367960438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031854674220085144, "target_z": -0.42382812271135556, "ce": 6.316492557525635, "genuineness": 3.798154592514038, "identity": 0.7062338590621948, "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_Sourness/e0cfdca4962d0aa9f89626cf7025af92b7627fd111edf70024f15d416676c781.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "e12e5cc6365d368f4cf5dbb5c2a997efc2a27ef77618e1ac09b63b964b235d03", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e06078a3de9b35c7d48d081f8ea59846a4de015ec8744c1956c28b7827ec5efc", "generation_seconds_batch": 18.273828412988223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1678132712841034, "target_z": -0.1093749838448627, "ce": 5.454712867736816, "genuineness": 3.8169827461242676, "identity": 0.5084352493286133, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e12e5cc6365d368f4cf5dbb5c2a997efc2a27ef77618e1ac09b63b964b235d03.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "e1b1dd3b5813be9604a20cd4e1c90b70012414fd6c5827f2fd5bc7dc33e1f25d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "970a818d95af77388334de31ae46d6267594e5b21f29a5f55d703609ee718a44", "generation_seconds_batch": 21.894793803920038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11967885494232178, "target_z": -0.2207031280964013, "ce": 5.998785495758057, "genuineness": 4.381826400756836, "identity": 0.7341467142105103, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e1b1dd3b5813be9604a20cd4e1c90b70012414fd6c5827f2fd5bc7dc33e1f25d.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "e1e834272196984d3bcbab60f270af4a71139245d0402170bc35e8d49983c6e1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "05f8fd15d686da6fcf8591016257fcd45d2b90f309c8617bc6fc40edd3a84b06", "generation_seconds_batch": 24.87641819694545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014965400099754333, "target_z": -0.4628906415590157, "ce": 5.998785495758057, "genuineness": 4.400654315948486, "identity": 0.7288862466812134, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e1e834272196984d3bcbab60f270af4a71139245d0402170bc35e8d49983c6e1.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "e24ed8307f976e69125ac3a8b0aac52cbeeff4092936b7dd99ac993cb46f4021", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e671d15fd72f942ed77ffd740a00b3859c6fb32eb26f6e93835858d7bb66bba0", "generation_seconds_batch": 23.782783022033982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04789946973323822, "target_z": -0.3867187642703713, "ce": 6.260893821716309, "genuineness": 4.017816066741943, "identity": 0.2336755245923996, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e24ed8307f976e69125ac3a8b0aac52cbeeff4092936b7dd99ac993cb46f4021.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": "e2695ecccd6035670a78f711cec854ca9799c726cc4f01cdd5e482610be89fa7", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89c722f3071d308eca2d80596f763e04cf0c7cc5a67f266a0e225d923c8fd6ec", "generation_seconds_batch": 20.60470909101423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2218589186668396, "target_z": 0.01562500753906407, "ce": 6.268836498260498, "genuineness": 4.2374773025512695, "identity": 0.669911801815033, "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_Sourness/e2695ecccd6035670a78f711cec854ca9799c726cc4f01cdd5e482610be89fa7.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "e2c404f1fd73dfb46f26f537d367f683e0aee5dc4f3a9104bf9b685412cb17e2", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "eab84a08fde260257d5d72a4e057fa0767cb2a47b190c12afbb6619f41d88773", "generation_seconds_batch": 19.37358506396413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12896795570850372, "target_z": -0.19921874273018822, "ce": 6.181467056274414, "genuineness": 4.143336772918701, "identity": 0.6826463341712952, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e2c404f1fd73dfb46f26f537d367f683e0aee5dc4f3a9104bf9b685412cb17e2.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "e2ec7301f4174226f34551b68dcd1230f7ed254597cc44fe674d341ba267d1f8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "21c4101525abb65dd77c389c2ebd7eb6b1061030799759857612bf53d1ee9eda", "generation_seconds_batch": 22.41437520692125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04705500602722168, "target_z": -0.3886718902127543, "ce": 6.181467056274414, "genuineness": 4.645420074462891, "identity": 0.7811236381530762, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la veille 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_Sourness/e2ec7301f4174226f34551b68dcd1230f7ed254597cc44fe674d341ba267d1f8.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": "e2f3381aed67e9b4fdfec147922d9d6dbe3ea3e78b5dec995ca856089788b024", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "74fa8fc61a236295006d3f1eef540929d4b9495e13bdfdb37f0ab770948df7df", "generation_seconds_batch": 14.503948878962547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1078563705086708, "target_z": -0.248046874057617, "ce": 6.1894097328186035, "genuineness": 4.400654315948486, "identity": 0.5545951128005981, "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_Sourness/e2f3381aed67e9b4fdfec147922d9d6dbe3ea3e78b5dec995ca856089788b024.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": "e374e9b8898c956c71177b100c20049306cdecf2f9c51570354f0ad5f9550e02", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ba54be564a232daadc3d21b42f0255b343cc1f954e8170e4280f86a210b88ec", "generation_seconds_batch": 23.81478811299894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2176366001367569, "target_z": 0.005859377827149026, "ce": 5.879645347595215, "genuineness": 4.394378662109375, "identity": 0.7659547924995422, "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_Sourness/e374e9b8898c956c71177b100c20049306cdecf2f9c51570354f0ad5f9550e02.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "e4406a556052b78a512eeee2ff84789edb46b35a53e8bf2d8e294bc8a01caee8", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "16a20c765a5e07f3fb142435ecc8574dcaaafe22332a3474e8a9235e75ef7eed", "generation_seconds_batch": 24.78559658303857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14416828751564026, "target_z": -0.16406251023158694, "ce": 6.125868320465088, "genuineness": 4.406930446624756, "identity": 0.5201276540756226, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e4406a556052b78a512eeee2ff84789edb46b35a53e8bf2d8e294bc8a01caee8.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "e5258871f984b2ad38f20c1adb7441b2b4220282473d323f3d700af118572261", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "525a1ec5b02215342e5e6a6776e6a9efab22a7d2c44e9bf125a4a0f9c5663288", "generation_seconds_batch": 17.4913608210627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11967885494232178, "target_z": -0.2207031280964013, "ce": 6.006728172302246, "genuineness": 4.432034492492676, "identity": 0.3731608986854553, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e5258871f984b2ad38f20c1adb7441b2b4220282473d323f3d700af118572261.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": "e5c0ec2f18fc30faa453d0e4407bb69892058a8cbb3a2e14085624a9a6b5bbce", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d8e78e9a00b8719a42fb606228f2bf8787528766a913037d6b154c2a4a8a3ce", "generation_seconds_batch": 24.029214910930023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4735089838504791, "target_z": 0.5976562626548575, "ce": 6.292664527893066, "genuineness": 4.369274139404297, "identity": 0.5887266993522644, "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_Sourness/e5c0ec2f18fc30faa453d0e4407bb69892058a8cbb3a2e14085624a9a6b5bbce.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "fe4ecbfd1bc5d3e56803a9416112729eda851a9fd1185bc58d9efd6ac25c0b67", "generation_seconds_batch": 17.46446179994382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10616744309663773, "target_z": -0.251953125942383, "ce": 6.356205940246582, "genuineness": 4.3504462242126465, "identity": 0.47749921679496765, "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_Sourness/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "e6fee8c1a98a992869fd59f732721b5af65ba1f1132cae889d7fae9e5bd1a7fd", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2954d4b4887c2385f59e55a5f3a1bd14d0a33f0da4563e92c9aed1004e7f94ea", "generation_seconds_batch": 17.90749287197832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08421139419078827, "target_z": -0.3027343832121948, "ce": 6.022613525390625, "genuineness": 4.582659721374512, "identity": 0.8034587502479553, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e6fee8c1a98a992869fd59f732721b5af65ba1f1132cae889d7fae9e5bd1a7fd.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "e76c49d36026fc0cbacce89758f00f8c606600228b43038695164d152c3a4dab", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "78fd48650233d66b4b0613c647ec36eb56f77062c7beed872269596742598137", "generation_seconds_batch": 24.43342513893731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 5.7684478759765625, "genuineness": 4.061748504638672, "identity": 0.7553168535232544, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e76c49d36026fc0cbacce89758f00f8c606600228b43038695164d152c3a4dab.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "e7a676628dc6014d2a9ca300924b2ebf487829586573a25191db7fd30281cdeb", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f48848cf0b975a5eb0df4105e3651c22b3ea76082c74f74323a60bc3bf66800", "generation_seconds_batch": 24.78559658303857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8163610696792603, "target_z": 1.3906249816908445, "ce": 6.213237762451172, "genuineness": 4.143336772918701, "identity": 0.5854446887969971, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e7a676628dc6014d2a9ca300924b2ebf487829586573a25191db7fd30281cdeb.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "e7ee4dcf70cb92fab509229ba2ca024969aeb125558e7edf03696979cd94b336", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b459ab14047f64bfa5460285856bd27aa56b419ed0496bab2faede0b62b4174a", "generation_seconds_batch": 25.285458549042232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23705925047397614, "target_z": 0.050781240037665334, "ce": 6.133810997009277, "genuineness": 4.030367851257324, "identity": 0.571329653263092, "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_Sourness/e7ee4dcf70cb92fab509229ba2ca024969aeb125558e7edf03696979cd94b336.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "e848cdbf0dbf62835df79b4bc789b82f9840ce37fe78e70c57197e57f69e93ec", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f64db7b1d7f4cda6f34213a8ae40526c81949e4467fe60a4465666960f0f14cd", "generation_seconds_batch": 25.729612956987694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021721109747886658, "target_z": -0.4472656340199517, "ce": 6.141753673553467, "genuineness": 4.381826400756836, "identity": 0.7570902109146118, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e848cdbf0dbf62835df79b4bc789b82f9840ce37fe78e70c57197e57f69e93ec.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "e8b51f4b89976a941fe48dfe4a191dc8626d294dc8395b3dfc6e69ca116df226", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "299d470e0db03f64af1791addccac65c5021ec70e3f60b3090a5856949d9a8d3", "generation_seconds_batch": 16.478162411018275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020876646041870117, "target_z": -0.4492187599623347, "ce": 6.141753673553467, "genuineness": 4.337893962860107, "identity": 0.38195616006851196, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e8b51f4b89976a941fe48dfe4a191dc8626d294dc8395b3dfc6e69ca116df226.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "e8cafe809e14d896cb51f758257d4b2fa95aa18190135896182467eeacf3016f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "817d9b34f3ac423c7adfb8790d093e56d756f6edf04a86d5e4cac4cac85ae315", "generation_seconds_batch": 25.006969840964302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22523677349090576, "target_z": 0.023437511308596105, "ce": 5.927301406860352, "genuineness": 4.18099308013916, "identity": 0.3079429268836975, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e8cafe809e14d896cb51f758257d4b2fa95aa18190135896182467eeacf3016f.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "e8df4e05400a95df295788a4b1b5716f8d246c9472bc2afbdc53dd46f9b5a45b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "de8a9f1e61aef3084b7762a7aa2f03e44acd893b56c2cc70c0eb2c647c7a5fda", "generation_seconds_batch": 22.73332710005343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12896795570850372, "target_z": -0.19921874273018822, "ce": 6.078212261199951, "genuineness": 4.15588903427124, "identity": 0.7119536399841309, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e8df4e05400a95df295788a4b1b5716f8d246c9472bc2afbdc53dd46f9b5a45b.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "e936ac0db44b2a541b6a4c5b4c0e48ca7e65427ff01af2332955516205ec7fac", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ff8537070d169ced5b3d9d18b14bef9a081cc504ad0bf03fc01d2f56a883ed50", "generation_seconds_batch": 22.999037294997834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01796865463256836, "target_z": -0.5390624843833672, "ce": 6.038498878479004, "genuineness": 4.432034492492676, "identity": 0.5881571769714355, "hypothesis": "J'ai trouvé la 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_Sourness/e936ac0db44b2a541b6a4c5b4c0e48ca7e65427ff01af2332955516205ec7fac.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "e980ef2ae551ab1e3eeac830cdef2d2195f60d0d3294a1aa10a8be93ddb38aa9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4e9911081306f7b44e4cbc83abafb1b21a2306375f2f249eba779ebf050e4087", "generation_seconds_batch": 23.509999967063777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14754614233970642, "target_z": -0.15625000646205492, "ce": 6.09409761428833, "genuineness": 4.3881025314331055, "identity": 0.4675864577293396, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e980ef2ae551ab1e3eeac830cdef2d2195f60d0d3294a1aa10a8be93ddb38aa9.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "e9aca4f046810d2c83371d65c5b323e4f36bee24a2ab4ac4b6f2dca890b1fea1", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0d3bfcab7d8574f64f497847c094f30353c8534cb572dddb44f6a4ccc1357d69", "generation_seconds_batch": 23.29144824494142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3046163320541382, "target_z": 0.20703128096401313, "ce": 5.71682071685791, "genuineness": 3.9048471450805664, "identity": 0.5426250696182251, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e9aca4f046810d2c83371d65c5b323e4f36bee24a2ab4ac4b6f2dca890b1fea1.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "4ff3cbeeb477e5e9fad45c397b88f781c943431a03d6434efe65614c691f34cc", "generation_seconds_batch": 18.861882584984414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04789946973323822, "target_z": -0.3867187642703713, "ce": 6.3641486167907715, "genuineness": 4.532451152801514, "identity": 0.4346294105052948, "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_Sourness/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "e9e92e8edfaac8aaf89876754c14757da990b052ce0cf2170d14a6f0954e7660", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c8759058eb360460bd4d85f10e873f91d92f23a451de3279888a530451a42309", "generation_seconds_batch": 21.407543204026297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02134650945663452, "target_z": -0.5468749881528994, "ce": 6.268836498260498, "genuineness": 4.143336772918701, "identity": 0.44746023416519165, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/e9e92e8edfaac8aaf89876754c14757da990b052ce0cf2170d14a6f0954e7660.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "ea8b76175c5c08abbbd79207164f72d8e0edf6e6e067655a27cfde028126a6bf", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a8efa6259b9109e17cd49902b6a04f017c5862ec3e039c4f373d4e4d86e8445a", "generation_seconds_batch": 17.315387034090236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09603388607501984, "target_z": -0.2753906200188327, "ce": 5.95112943649292, "genuineness": 4.21237325668335, "identity": 0.5811907649040222, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ea8b76175c5c08abbbd79207164f72d8e0edf6e6e067655a27cfde028126a6bf.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "ea9575e26c0a4f6c5cf4f1c8c02d4eae2628ae2698bcb2754d9f9becd15051b6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7d347bdecc8818a4ba6b992b179102c39e96fbcdfbb44a44576f0ec5704c8a67", "generation_seconds_batch": 18.752136463997886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06225535273551941, "target_z": -0.35351562324986013, "ce": 6.086154937744141, "genuineness": 4.607763767242432, "identity": 0.5879297256469727, "hypothesis": "J'ai trouvé la 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_Sourness/ea9575e26c0a4f6c5cf4f1c8c02d4eae2628ae2698bcb2754d9f9becd15051b6.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": "eb4b274df65869c880d6119e7e362ed90c3b2eec84a2c0de0e00c6339bf12ae6", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae19280bf67d3311cc8fb0b8d34d29518b774f0fcd6937469e6df2658054bf43", "generation_seconds_batch": 23.81478811299894, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 6.109982967376709, "genuineness": 4.356721878051758, "identity": 0.7840978503227234, "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_Sourness/eb4b274df65869c880d6119e7e362ed90c3b2eec84a2c0de0e00c6339bf12ae6.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": "eb50996df7b556ee113a49046d5cca21e8d823f3a3f106d0f28254787d9dc4d5", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "38b7d358c0e9ab8c4f7e96c9e86d3678e4431f2c70314cd43093484b3b0ce21f", "generation_seconds_batch": 14.461816993076354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02594342827796936, "target_z": -0.4375000043080366, "ce": 6.125868320465088, "genuineness": 4.432034492492676, "identity": 0.5472168922424316, "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_Sourness/eb50996df7b556ee113a49046d5cca21e8d823f3a3f106d0f28254787d9dc4d5.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": "eb7313a7d1e97fbf59acc4f159eb5070a3eeff3294459f2334678c7c29f8db12", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Your message arrived after I had left.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca716b114785ad213f5dd6428249f4ac92bb757ac95c4ececcbb7a0099fd5eae", "generation_seconds_batch": 16.023285418981686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3400837779045105, "target_z": 0.2890625016155137, "ce": 6.340320587158203, "genuineness": 4.086852550506592, "identity": 0.40063613653182983, "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_Sourness/eb7313a7d1e97fbf59acc4f159eb5070a3eeff3294459f2334678c7c29f8db12.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": "eb7ba37b56f2a912019ee85d716405f920cabdb876bd125e44dcb852cf2485ab", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "232c0e11b8a62a19adf20fbf313f9b5580087dd3b164f3d04d46ca8b2db3dd4c", "generation_seconds_batch": 23.13393048790749, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032699137926101685, "target_z": -0.42187499676897255, "ce": 6.157639026641846, "genuineness": 4.400654315948486, "identity": 0.6595615148544312, "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_Sourness/eb7ba37b56f2a912019ee85d716405f920cabdb876bd125e44dcb852cf2485ab.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": "ebaa1debecea3a0e8b740b7a340e630ed2307ad7fa601b4153e713afe37dfaf3", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54bff812a576ed6f0ae19272cb3022c39a5d5a7af41060e4b15b3d8e0d29f5ef", "generation_seconds_batch": 18.56141291500535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18976931273937225, "target_z": -0.05859374380719737, "ce": 6.284721851348877, "genuineness": 4.494794845581055, "identity": 0.5245713591575623, "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_Sourness/ebaa1debecea3a0e8b740b7a340e630ed2307ad7fa601b4153e713afe37dfaf3.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": "ebdbd287625bbdea9e24414eb2472f02eff490cdbdd0047c173399303fda0397", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25378403c30bd5a6ddcc21049dd35b0884097d02015376ddf0376d230a16ca8a", "generation_seconds_batch": 14.520992433070205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21594767272472382, "target_z": 0.001953125942383009, "ce": 5.879645347595215, "genuineness": 4.1998209953308105, "identity": 0.4463733434677124, "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_Sourness/ebdbd287625bbdea9e24414eb2472f02eff490cdbdd0047c173399303fda0397.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "e97d9045a4fee6a2e23bcd6cc2600e5cab4b63fe3a641552f8ec570d25a71564", "generation_seconds_batch": 17.512150016031228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15176846086978912, "target_z": -0.14648437675013987, "ce": 6.086154937744141, "genuineness": 4.432034492492676, "identity": 0.64892578125, "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_Sourness/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "ec8ffb484a74cdc3e00f34336220e3a89ad407753d7ca2fa09478260e5429739", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5574d51b286231218ed005553d1937f745f231d7f8599d7c56bd13fba295951f", "generation_seconds_batch": 24.535825594095513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.054384231567383, "genuineness": 4.6203155517578125, "identity": 0.6269407272338867, "hypothesis": "J'ai trouvé la 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_Sourness/ec8ffb484a74cdc3e00f34336220e3a89ad407753d7ca2fa09478260e5429739.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "ecbd3209d6a1ae614f6a2c238a19c26befc7d7e62a65a4cbeaa1e3ecddb635f5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a127501fe1aac73a42bfa45ce04295706cc453465cb2f85426bf27f7224a27a0", "generation_seconds_batch": 23.685977277928032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.221180438995361, "genuineness": 4.469690799713135, "identity": 0.3783268928527832, "hypothesis": "I f found the little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ecbd3209d6a1ae614f6a2c238a19c26befc7d7e62a65a4cbeaa1e3ecddb635f5.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "eccbb363ac7b256b3a6d5bd9fed060e785edf671975ec28e8d431a5a579bfa8a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "23f02c307e0a8aa1348a099673f27f2d1799709674a84d08badb694bbeba530d", "generation_seconds_batch": 25.541611508000642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01965758204460144, "target_z": -0.5429687362681334, "ce": 6.221180438995361, "genuineness": 4.281409740447998, "identity": 0.5088376402854919, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/eccbb363ac7b256b3a6d5bd9fed060e785edf671975ec28e8d431a5a579bfa8a.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "ed49f831449b45510b95299e5472ce0d96cf2876af3f5a5cd3d4da67944aacb0", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9b24ba47a4ece80a3f0edf033c8e889687aef3f2f7731dbdaf69664c5af84b4f", "generation_seconds_batch": 26.577459005988203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1179899275302887, "target_z": -0.22460937998116734, "ce": 6.062326908111572, "genuineness": 4.293961524963379, "identity": 0.42511647939682007, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ed49f831449b45510b95299e5472ce0d96cf2876af3f5a5cd3d4da67944aacb0.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "ed50843125284772eb84b51ce93e78bc1588527b0498a6c7827bffecf1a62d7f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ba6afed1a7d9005fbd8d4f417bb5ad81441cce4d27d919638359a38fb657a613", "generation_seconds_batch": 17.6255942779826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10870083421468735, "target_z": -0.246093748115234, "ce": 6.062326908111572, "genuineness": 4.256305694580078, "identity": 0.7128968238830566, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ed50843125284772eb84b51ce93e78bc1588527b0498a6c7827bffecf1a62d7f.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "ede1a1a96df6ef308297bfc43d3f9bd5ebae52c06f81403a396f0c1e5d72a637", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "98c630913dbfeb6b960362d657aa6287cc8b438a5a665f03501cc5b329c437ba", "generation_seconds_batch": 22.688849003985524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10701190680265427, "target_z": -0.25, "ce": 5.442798614501953, "genuineness": 4.287685871124268, "identity": 0.7408573627471924, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ede1a1a96df6ef308297bfc43d3f9bd5ebae52c06f81403a396f0c1e5d72a637.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": "edf2cef6f371f9036be50f075b0cd132fa10e3f56f6bb3546e33d41dd84bd2b0", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "13c853d89ec3bf71c25a2588e6c2030a5d684833a4d19e9b5c3a6d48162565db", "generation_seconds_batch": 16.44014199101366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02509896457195282, "target_z": -0.4394531302504196, "ce": 5.998785495758057, "genuineness": 4.482243061065674, "identity": 0.7473844885826111, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lise le bien et vérifie les deux derniers chiffres. Appelle-moi quand il auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/edf2cef6f371f9036be50f075b0cd132fa10e3f56f6bb3546e33d41dd84bd2b0.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": "efccf36af346203c9cfaa416a65a78f2f948cc81bba4a7f78d6470e08317b4ef", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c6ac5c70b03d3261c9f36b24135b1a66f1825dab99ddae5bf461720712470c18", "generation_seconds_batch": 20.192119134007953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04705500602722168, "target_z": -0.3886718902127543, "ce": 6.125868320465088, "genuineness": 4.369274139404297, "identity": 0.7662662267684937, "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_Sourness/efccf36af346203c9cfaa416a65a78f2f948cc81bba4a7f78d6470e08317b4ef.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "f0731768eb173a59c52025e5b4785dfafc17a4c3667c0865faf90511a7f1d169", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "df83dea3d891db2f2232939fa5395d924713c37181ddc3d08ea39b91c32cbbf4", "generation_seconds_batch": 24.154377440921962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032699137926101685, "target_z": -0.42187499676897255, "ce": 6.348263263702393, "genuineness": 4.419482707977295, "identity": 0.647156298160553, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f0731768eb173a59c52025e5b4785dfafc17a4c3667c0865faf90511a7f1d169.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "f07453218f259f13e222b4de4efbfc0b1f45fc39ecce44702555023e401be6e7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "135536d6850da949b7526e2f902db554181a2ba928e3f1861a84f1f378d3a95a", "generation_seconds_batch": 17.699199733906426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27083778381347656, "target_z": 0.1289062432686928, "ce": 5.772419452667236, "genuineness": 3.8169827461242676, "identity": 0.5525261163711548, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f07453218f259f13e222b4de4efbfc0b1f45fc39ecce44702555023e401be6e7.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "f0a47bf08d2f1bbe65583a73204d28b383e5481b9ef60b1815511d1df8b4a3e6", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9ad4f88326b534da8932be3c32da012027ab7b18c5cac84027aa42169c880e2a", "generation_seconds_batch": 24.43342513893731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09856727719306946, "target_z": -0.2695312421916836, "ce": 5.2640886306762695, "genuineness": 3.860914945602417, "identity": 0.6007422804832458, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f0a47bf08d2f1bbe65583a73204d28b383e5481b9ef60b1815511d1df8b4a3e6.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "f0a94dddd442fe55a58705674b666350a3f1f6b6a41a599d6ae74bbece07b747", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7a38ed51fe4030b4d8fbc8b122a6a8941deaac6a655527e150f86852e3dceec3", "generation_seconds_batch": 17.843615421094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08843371272087097, "target_z": -0.29296875350027973, "ce": 6.157639026641846, "genuineness": 4.231201171875, "identity": 0.680363655090332, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f0a94dddd442fe55a58705674b666350a3f1f6b6a41a599d6ae74bbece07b747.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": "f0e8dd5b0a2c6c0c5ecaf4c5bc55fc62de6c17043ac86ece3d1154d730aa64dd", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e97a59d22f6a3104b4dc99a1a33467ca54d46990b524414b461c28538b3e6964", "generation_seconds_batch": 22.76971100596711, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0951894223690033, "target_z": -0.2773437459612157, "ce": 6.229123115539551, "genuineness": 4.268857479095459, "identity": 0.44940924644470215, "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_Sourness/f0e8dd5b0a2c6c0c5ecaf4c5bc55fc62de6c17043ac86ece3d1154d730aa64dd.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "f0f485ff8b3c2c702230d00e2af8b03a61f0c709f5df25af0249dab797a3762b", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "83dc98fe750697ddd57370e2bbd94425a34e6df466f0d53937220d8df7b0d01c", "generation_seconds_batch": 23.972637524013408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11883439123630524, "target_z": -0.22265625403878433, "ce": 6.0146708488464355, "genuineness": 4.256305694580078, "identity": 0.24630987644195557, "hypothesis": "De deur 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_Sourness/f0f485ff8b3c2c702230d00e2af8b03a61f0c709f5df25af0249dab797a3762b.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "f12af501e56fb067322f5daa3f98a0bbd6742b6e1d0da3391d27b4053ca2152a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "68a147b62b3a7d30396b6b5b00d05ccd65a7668445a30043aad200e1d414c12b", "generation_seconds_batch": 18.641499327961355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012432023882865906, "target_z": -0.46874998492187187, "ce": 5.998785495758057, "genuineness": 3.7416701316833496, "identity": 0.4707604944705963, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f12af501e56fb067322f5daa3f98a0bbd6742b6e1d0da3391d27b4053ca2152a.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "f159f85113bb67bcf41131317100cf419852721e93b6d6001c5e3ad3b122b113", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d7aaff824f557f1edd9e0559b0431944b514bf75787134c67a7cc2763e56aef1", "generation_seconds_batch": 24.261224566027522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2514151334762573, "target_z": 0.08398438105817649, "ce": 5.855817794799805, "genuineness": 4.20609712600708, "identity": 0.686404287815094, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f159f85113bb67bcf41131317100cf419852721e93b6d6001c5e3ad3b122b113.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "f19e3263ef640c581c7fd3c4480af76a6a18a5e1584cf41efb7dd3705c73c0b2", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7b17aad44ac133db8485c2a3512f6cd7efd85925ac52fc748ecfcc51972a7786", "generation_seconds_batch": 24.24780233798083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5376881957054138, "target_z": 0.7460937653473805, "ce": 6.117925643920898, "genuineness": 4.036643981933594, "identity": 0.6764059662818909, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f19e3263ef640c581c7fd3c4480af76a6a18a5e1584cf41efb7dd3705c73c0b2.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "f1f7c764e0808cfddfaac5d84f4ab82bc8c883312fc1e530e353fa946d78c299", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1822a2cd28f88c2122a402cf542527f4d796fda44fb2d5e09eaaa2e7f7853b16", "generation_seconds_batch": 17.39045716205146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05127732455730438, "target_z": -0.37890626050083925, "ce": 6.229123115539551, "genuineness": 4.1998209953308105, "identity": 0.2163791060447693, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f1f7c764e0808cfddfaac5d84f4ab82bc8c883312fc1e530e353fa946d78c299.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "f2179b62adc0784564e9cf65313ac76d0431ed18f34c6f983ff89b595642c2f9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "80b5b2b2f732491186e5ab91dc9eea10c661b35edb4058f79b6c2ecdfe44032d", "generation_seconds_batch": 23.86193348793313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20834749937057495, "target_z": -0.01562500753906407, "ce": 5.879645347595215, "genuineness": 3.936227321624756, "identity": 0.5452026724815369, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f2179b62adc0784564e9cf65313ac76d0431ed18f34c6f983ff89b595642c2f9.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "1df4e6a59d6040dd84262d3bade759f7a22b4cea109404c189479e6979685f5c", "generation_seconds_batch": 17.417397539014928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032699137926101685, "target_z": -0.42187499676897255, "ce": 6.300607204437256, "genuineness": 4.519899368286133, "identity": 0.7172011137008667, "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_Sourness/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "f25a734ff7e69fea4d56316e61978e592fa2d6053d35d4c512e7dcd3a4e7e56c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dcf7dae8efeb416ef598a941dba6d1a1872faf4c26c75d67155020be0793de52", "generation_seconds_batch": 24.31401565298438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4397304654121399, "target_z": 0.519531293888123, "ce": 6.038498878479004, "genuineness": 4.168440818786621, "identity": 0.7181751728057861, "hypothesis": "Ik heb het kleine dosje 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_Sourness/f25a734ff7e69fea4d56316e61978e592fa2d6053d35d4c512e7dcd3a4e7e56c.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": "f3242c92d002f3670019c660a1cd1900bbaee5e9dc4883743242ea9765a238a3", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fea7ef13676d78a6814e36fcb07252afb70a43bd51b9abed04d63e21bb4c9db5", "generation_seconds_batch": 14.359492246992886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33248358964920044, "target_z": 0.27148433366977376, "ce": 6.348263263702393, "genuineness": 4.545003414154053, "identity": 0.6663617491722107, "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_Sourness/f3242c92d002f3670019c660a1cd1900bbaee5e9dc4883743242ea9765a238a3.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "f3c3e777189cb719b19eb88850146ef6fdf549f24b4cd5da896b35f7d6160d7a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5952bdc7a27cf52561b379569e683e4c3497d39793718ea00783300212f34b6f", "generation_seconds_batch": 17.4913608210627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1576797068119049, "target_z": -0.1328124951534588, "ce": 5.998785495758057, "genuineness": 4.055472373962402, "identity": 0.5657296776771545, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f3c3e777189cb719b19eb88850146ef6fdf549f24b4cd5da896b35f7d6160d7a.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "f46150feef5227dfa2cd134f88f4657f0d020ef06fbdc762af43a32bab4c35c4", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c5f57efbe290a0433f39aa99cdfcd2ff02e0b46d66601b5850c500f69c9e651a", "generation_seconds_batch": 23.90696645900607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16950219869613647, "target_z": -0.10546873196009669, "ce": 5.990842819213867, "genuineness": 3.7416701316833496, "identity": 0.3197491765022278, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f46150feef5227dfa2cd134f88f4657f0d020ef06fbdc762af43a32bab4c35c4.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": "f488afcb6cf976fad4db93d1f24c86527b699170297ddc4275c8ead99e460aed", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The road turns left behind the bridge.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1293e6ba4fd6f64ae9cc28df4039e58f00fb41f53b118b532d8a2cc8cc0869df", "generation_seconds_batch": 24.610442682984285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1492350697517395, "target_z": -0.1523437545772889, "ce": 6.372091293334961, "genuineness": 4.356721878051758, "identity": 0.46937692165374756, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f488afcb6cf976fad4db93d1f24c86527b699170297ddc4275c8ead99e460aed.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "f4b9fefb0f0273a7aeea4227dc7c21ac66bdccf675ff6e22637ed74274d53318", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6b926aa3f0730787d5e15f3de0b82360227990fc6f352ce2c626e4f6dde96341", "generation_seconds_batch": 19.576854366925545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06647767126560211, "target_z": -0.3437499935379451, "ce": 5.95112943649292, "genuineness": 4.017816066741943, "identity": 0.6427291035652161, "hypothesis": "Ik 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_Sourness/f4b9fefb0f0273a7aeea4227dc7c21ac66bdccf675ff6e22637ed74274d53318.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "f5489cd20a591112106b6d1152ba64cdfea8a9a7d0fbcbe8cf85eb7a374f1d6d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3ca9b25ce34ca07c85906819832bcf42ee923c549ccbf60604e488355d06b882", "generation_seconds_batch": 16.328655909979716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3071497082710266, "target_z": 0.21289062432686928, "ce": 6.197352409362793, "genuineness": 4.18099308013916, "identity": 0.8038865327835083, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f5489cd20a591112106b6d1152ba64cdfea8a9a7d0fbcbe8cf85eb7a374f1d6d.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "f5619d7834d010093c30b10dc1a3e83ae34ea8624c859f5bf046a8ef5a8ec0f7", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3491cc1480232e4614abb77d15beae233d68ca1dede6c178f055d33af400a852", "generation_seconds_batch": 23.62936045206152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10194512456655502, "target_z": -0.26171875565429803, "ce": 5.855817794799805, "genuineness": 4.319066047668457, "identity": 0.32018065452575684, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f5619d7834d010093c30b10dc1a3e83ae34ea8624c859f5bf046a8ef5a8ec0f7.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "f59d6ae6c850c6b7bf6230f6550073f12a7d85d187b35e65307d29c98da24017", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b7795e0474973641c0e427336460138ccafddb676d5504f092afe6144217ca13", "generation_seconds_batch": 26.917664909968153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09603388607501984, "target_z": -0.2753906200188327, "ce": 6.078212261199951, "genuineness": 4.595211505889893, "identity": 0.6057645678520203, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f59d6ae6c850c6b7bf6230f6550073f12a7d85d187b35e65307d29c98da24017.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "f59e061161093b4868a312bc8c9c73a86566df624045887d6d5aefe458af0f17", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a5b22144eba2aa9b6e0eb5facb2440163ff682d850cb658f968d210ed1972820", "generation_seconds_batch": 21.614174754009582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0766112208366394, "target_z": -0.32031251669364186, "ce": 5.673136234283447, "genuineness": 4.068024158477783, "identity": 0.670091450214386, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f59e061161093b4868a312bc8c9c73a86566df624045887d6d5aefe458af0f17.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "f620048a6c559943285d20ecc4caf1914329d13f22d4b84b6ee1c06c6bd05c1a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "18bdf718e0e9d4b3afa775271d8c91313eddb09961b979ea89f063cd17328886", "generation_seconds_batch": 22.524807608919218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01290188729763031, "target_z": -0.5273437631933621, "ce": 6.308549880981445, "genuineness": 4.482243061065674, "identity": 0.40358465909957886, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f620048a6c559943285d20ecc4caf1914329d13f22d4b84b6ee1c06c6bd05c1a.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": "f649a70bf33388c3c31ad7c8450790d479b631d491ed2dfe41653705a8a3cc62", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Your message arrived after I had left.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e782d4761432b393d3de506c716b2f3b48ee5e230c15a5e1a8c149f2827042d", "generation_seconds_batch": 16.023285418981686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 6.594485759735107, "genuineness": 4.13078498840332, "identity": 0.3072577118873596, "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_Sourness/f649a70bf33388c3c31ad7c8450790d479b631d491ed2dfe41653705a8a3cc62.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "f65c9e80f809171e83b799132e8290849007f531ab59822d1f383f8f313928d9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "325afb37f4249b93befa1f7bd701be9438017bf64184dd93290ad59fc54c8f1e", "generation_seconds_batch": 22.515159595990553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2573263645172119, "target_z": 0.09765622819056466, "ce": 6.09409761428833, "genuineness": 3.9927117824554443, "identity": 0.2397764027118683, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f65c9e80f809171e83b799132e8290849007f531ab59822d1f383f8f313928d9.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "f682d492b1cecb778d8fe37e5d3d485416629c71304b68cc2de73988ba3f0c75", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f858956f28e258af7f55961f1769d2146a9c53b3f4bc304e8eb0b439b3ae24c5", "generation_seconds_batch": 24.00901875901036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09350049495697021, "target_z": -0.2812499978459817, "ce": 6.09409761428833, "genuineness": 4.13078498840332, "identity": 0.5614758729934692, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f682d492b1cecb778d8fe37e5d3d485416629c71304b68cc2de73988ba3f0c75.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "f6844f255a23ce87de5261391d220c96dafc7b7bf760970026a2ee82648f87d5", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "521b7689fd0d56bb5994d8bf0df3607b35a1fe128e4948208807e670302aed26", "generation_seconds_batch": 25.264432463096455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2742156386375427, "target_z": 0.13671874703822484, "ce": 5.863759994506836, "genuineness": 3.8420867919921875, "identity": 0.35433974862098694, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f6844f255a23ce87de5261391d220c96dafc7b7bf760970026a2ee82648f87d5.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "f6c082c63dd86c861ec85cd520b2c18723d8e2a9ddeea96cb48b5f9db0ec2989", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bdfa17463eb28ee31a6c5300879b67c1c88483721cc9cdfbffe03e9921cd1580", "generation_seconds_batch": 22.912896441062912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14416828751564026, "target_z": -0.16406251023158694, "ce": 5.935244083404541, "genuineness": 3.9676074981689453, "identity": 0.5664697885513306, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f6c082c63dd86c861ec85cd520b2c18723d8e2a9ddeea96cb48b5f9db0ec2989.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": "f6d5cc944231a282dc3dc905d102658d5d7495173cac6a1b84a02e9446711584", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7f4693c6a0c9ba673fa914a1e96cde061890fde5d8d6621a983a14ff3497eb57", "generation_seconds_batch": 15.426428108941764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29786062240600586, "target_z": 0.19140627342494906, "ce": 6.292664527893066, "genuineness": 4.457139015197754, "identity": 0.3516439199447632, "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_Sourness/f6d5cc944231a282dc3dc905d102658d5d7495173cac6a1b84a02e9446711584.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "ebef26a59627fc6d857bb9fb789263109272c2cd99560e548829cdcd38cf48d3", "generation_seconds_batch": 17.671590415993705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05127732455730438, "target_z": -0.37890626050083925, "ce": 6.086154937744141, "genuineness": 4.457139015197754, "identity": 0.7337478995323181, "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_Sourness/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "f835c93a6b7ad56780a67425becc1a233347d1675dddf8fbf3fb757dcf9db83f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "216643268a9937bf235cb2c69254a05ee17a4646c35073487b91fcdb94cb5b47", "generation_seconds_batch": 18.583175281994045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029321283102035522, "target_z": -0.4296875005385046, "ce": 6.38003396987915, "genuineness": 4.369274139404297, "identity": 0.46852174401283264, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f835c93a6b7ad56780a67425becc1a233347d1675dddf8fbf3fb757dcf9db83f.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_Sourness", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": "7919e0c196ef79dbf21aa8d2dbf5a67e94e6abadd6618df26172b4a9337e347c", "generation_seconds_batch": 17.865553620038554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07576677203178406, "target_z": -0.322265608171732, "ce": 6.340320587158203, "genuineness": 4.557555198669434, "identity": 0.6952295303344727, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zum kleinen Holstor. Ich warte auf der anderen Seite.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "f8a8f311cff605b6ff3a934678f1785b2562ba4106477cccf024d370bdd76deb", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "34f43a78cb5b19976b0c21c1cf8053d67d9e4f1dc707919ddb54137a490ef8bf", "generation_seconds_batch": 16.758592555997893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0010793954133987427, "target_z": -0.5, "ce": 6.348263263702393, "genuineness": 4.432034492492676, "identity": 0.3300977945327759, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f8a8f311cff605b6ff3a934678f1785b2562ba4106477cccf024d370bdd76deb.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": "f8b02a0a8d8976478d0f205d85563779da1dd4f78bacd6cb1b0e846e75badaac", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The keys are on the kitchen table.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57d3c93eb7702000184e43f1f7283dfa505293823bc730fd2010f872b581573e", "generation_seconds_batch": 16.09574150305707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12559010088443756, "target_z": -0.20703124649972024, "ce": 6.213237762451172, "genuineness": 3.936227321624756, "identity": 0.5353695750236511, "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_Sourness/f8b02a0a8d8976478d0f205d85563779da1dd4f78bacd6cb1b0e846e75badaac.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "f90144bfac0b0735e396af8b085c9a25292b07f51da674c0baa986f520b3d423", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c5b01d5216b301b99e6080f7caf3b8e3f18e1f5b28bc47fe3f9e1dc8971247f3", "generation_seconds_batch": 24.515852708020248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0039873868227005005, "target_z": -0.48828124434570197, "ce": 6.23706579208374, "genuineness": 4.256305694580078, "identity": 0.41621899604797363, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f90144bfac0b0735e396af8b085c9a25292b07f51da674c0baa986f520b3d423.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "f90fb0d9288277d4e5b1c795e2b8c21bbdf23d5148c264952aa01db31ac91d94", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5a85ae3ff0f6f00d9b09c584ea15b718992c89236b5fa5fc22a6cf8e1a46241b", "generation_seconds_batch": 18.48414045199752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6407127380371094, "target_z": 0.9843750613895217, "ce": 6.181467056274414, "genuineness": 4.300237655639648, "identity": 0.3376036584377289, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f90fb0d9288277d4e5b1c795e2b8c21bbdf23d5148c264952aa01db31ac91d94.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "f912116e81533324c1ea26721b29a3506e8ee5ee8d3deb955081456e725b93e9", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4bc5603c86b47de2cf597f5ba34f884ab17a2bce13c8ce77163a7be3b4b15cd9", "generation_seconds_batch": 26.987835936015472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0723889172077179, "target_z": -0.330078111941264, "ce": 6.046441555023193, "genuineness": 4.632867813110352, "identity": 0.7190424203872681, "hypothesis": "J'ai trouvé la 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_Sourness/f912116e81533324c1ea26721b29a3506e8ee5ee8d3deb955081456e725b93e9.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": "f943fc429799eb96c66eb13499f7890740fa15577cc0559c59786fa3d78b0dd1", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f34af00a453fee617b8d9aa52062d4e83fb5c422608ad6a46d2fd34c433f18fc", "generation_seconds_batch": 22.76971100596711, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6508462429046631, "target_z": 1.0078124348409463, "ce": 6.221180438995361, "genuineness": 4.2249250411987305, "identity": 0.6173949241638184, "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_Sourness/f943fc429799eb96c66eb13499f7890740fa15577cc0559c59786fa3d78b0dd1.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": "f96a3ac2fe64f67a85a289e50b17b531861615288de689d7ae0dc247d4b5f3d3", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I wrote the number on the envelope.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2044d278be1de2c95040bf5f34629e37d6fbe03d519856295e910ae5a7ae5366", "generation_seconds_batch": 22.650942674954422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11714546382427216, "target_z": -0.22656250592355034, "ce": 6.2767791748046875, "genuineness": 3.936227321624756, "identity": 0.4376388192176819, "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_Sourness/f96a3ac2fe64f67a85a289e50b17b531861615288de689d7ae0dc247d4b5f3d3.mp3" }, { "id": "emo_Sourness-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-0", "key": "f9ecdf417d5bccb740ae1f2cda47c7107f4d01cfb721fc12e8f805ebf9fc6461", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La porte est encore ouverte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "029d9abd5acdc91488c9f2262fd56245fd3106296a59fb5ebe5b0b35cc35e641", "generation_seconds_batch": 23.940836893976666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10025619715452194, "target_z": -0.2656250075390641, "ce": 6.205295085906982, "genuineness": 4.545003414154053, "identity": 0.6868141889572144, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/f9ecdf417d5bccb740ae1f2cda47c7107f4d01cfb721fc12e8f805ebf9fc6461.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "fa68c3daaef9367bc25c62fa55e1e424dc77b1efa29cf59a51e8bb1136d47867", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a837ac47e8dffe09fab647e57ab8740949993fd4c2954185104784ea97c4c50", "generation_seconds_batch": 25.264432463096455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01290188729763031, "target_z": -0.5273437631933621, "ce": 6.38003396987915, "genuineness": 4.532451152801514, "identity": 0.33295565843582153, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fa68c3daaef9367bc25c62fa55e1e424dc77b1efa29cf59a51e8bb1136d47867.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "fa821c60fc9d08d259d20271b6db2e04742a4b023ca8d8e487e8be4ddd471cbd", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e154490af496f75e1af93703d43696e4bbb1db55ec6e973e5dfd2ed09db5625f", "generation_seconds_batch": 18.254128454020247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07407784461975098, "target_z": -0.326171860056498, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.6844809055328369, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fa821c60fc9d08d259d20271b6db2e04742a4b023ca8d8e487e8be4ddd471cbd.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "fa98f552ca7754b79bd60c38aec3c20b28da7db205347dc7b77820dbd6e38831", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d5e0f83c7e71d7c0875262553bd9deff9303fc01e8c593d13a8e5b3426273c3e", "generation_seconds_batch": 23.785128592979163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007835105061531067, "target_z": -0.515625007539064, "ce": 6.268836498260498, "genuineness": 4.406930446624756, "identity": 0.38967809081077576, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fa98f552ca7754b79bd60c38aec3c20b28da7db205347dc7b77820dbd6e38831.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "fac59cf873759d57542015736ba616fa63e7e823e12c9f98100ffc1b16516e1d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "43e67df5a3e3cefabf141670d656942fb3352a563fb2d335b81f3b296c304bdd", "generation_seconds_batch": 23.90696645900607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8062275052070618, "target_z": 1.3671874703822482, "ce": 5.935244083404541, "genuineness": 3.4247303009033203, "identity": 0.5758479237556458, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fac59cf873759d57542015736ba616fa63e7e823e12c9f98100ffc1b16516e1d.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "fb0006a3b7c5e75263681fb1f33207b2d2756622840b79fd5dd229b4a9f2716d", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "494ecd540200567887cd98b922522bce539403713e5921b8a71a7305175505f6", "generation_seconds_batch": 23.39210286992602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13741257786750793, "target_z": -0.17968751777065103, "ce": 5.911416053771973, "genuineness": 4.137060642242432, "identity": 0.6000580191612244, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fb0006a3b7c5e75263681fb1f33207b2d2756622840b79fd5dd229b4a9f2716d.mp3" }, { "id": "emo_Sourness-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-fr-1", "key": "fbdd76448547e5088460171f19b49375c016f6cf226c504a91459e57ec8a1227", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b2760238c8dea11c610aa2516d9990a27f0f81f8c28f8ecf6e6043042c0e4572", "generation_seconds_batch": 22.1632325979881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12559010088443756, "target_z": -0.20703124649972024, "ce": 5.657250881195068, "genuineness": 3.8671910762786865, "identity": 0.7702383995056152, "hypothesis": "J'ai trouvé la 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_Sourness/fbdd76448547e5088460171f19b49375c016f6cf226c504a91459e57ec8a1227.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "fbde062a56978e7a28584e3a53b50af448e4d836a54956112ae51996ae67fd92", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "681e72ca088ee2d761248fafea58d22081bf59be70c9632352dba79aafdcc9f2", "generation_seconds_batch": 18.684920288040303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1762578934431076, "target_z": -0.08984375888532552, "ce": 5.708878040313721, "genuineness": 3.898571252822876, "identity": 0.5028188228607178, "hypothesis": "De deur 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_Sourness/fbde062a56978e7a28584e3a53b50af448e4d836a54956112ae51996ae67fd92.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "fbfc0d43ee24198a99cec3891f67b4ff79476a972c275a5a7ffefa52269d92ff", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fb90630d0ff78faf105ee33711e57532ec7939a9ac150a7d53de602521cc1e43", "generation_seconds_batch": 25.160149175091647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3873737156391144, "target_z": 0.39843748546037644, "ce": 6.0146708488464355, "genuineness": 4.061748504638672, "identity": 0.5244868993759155, "hypothesis": "De durf staat nog open. Ik heb het jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fbfc0d43ee24198a99cec3891f67b4ff79476a972c275a5a7ffefa52269d92ff.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "fc1062bb7b0b842610d07dcaebfbce69934229cd2f9837e4728d287310cc3e18", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "dd8413780293112900dfa008aa9656d510c4423d76220fd424c5833f40e84342", "generation_seconds_batch": 24.110933082993142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054655179381370544, "target_z": -0.3710937567313072, "ce": 5.982900142669678, "genuineness": 4.168440818786621, "identity": 0.48202046751976013, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fc1062bb7b0b842610d07dcaebfbce69934229cd2f9837e4728d287310cc3e18.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": "fc8180fbbba22311250969f46544d7c11fb2e11434814f154dd6f5972030efc5", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "360241a2b5716a3ed7f8677c89c214aa8e1789ee4e6553803963dd4384e2089a", "generation_seconds_batch": 17.196808891021647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1036340519785881, "target_z": -0.257812503769532, "ce": 6.117925643920898, "genuineness": 4.18099308013916, "identity": 0.6473495364189148, "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_Sourness/fc8180fbbba22311250969f46544d7c11fb2e11434814f154dd6f5972030efc5.mp3" }, { "id": "emo_Sourness-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-1", "key": "fcd0bdb4d0266241b9560883d33420755811ff85fbd054fadc197cc8fb250bd3", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] He encontrado la cajita.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "666899d44350a9f566cc90ad384a1dfc8f505e0f529f35ba9bf1fd650524d7ef", "generation_seconds_batch": 16.551035907003097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1323457956314087, "target_z": -0.19140627342494906, "ce": 5.732706069946289, "genuineness": 4.036643981933594, "identity": 0.6033148169517517, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fcd0bdb4d0266241b9560883d33420755811ff85fbd054fadc197cc8fb250bd3.mp3" }, { "id": "emo_Sourness-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-0", "key": "fcd66ff4f896feb42a90b59616ff7966d7e093ad8cebd1e99769621798a967de", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] De deur staat nog open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b736317113a5aefc05085c3974a7e1afe2bdc7b6b41cd534ec710db36f02356d", "generation_seconds_batch": 18.684920288040303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18301360309123993, "target_z": -0.07421875134626144, "ce": 6.197352409362793, "genuineness": 4.2751336097717285, "identity": 0.6230862140655518, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fcd66ff4f896feb42a90b59616ff7966d7e093ad8cebd1e99769621798a967de.mp3" }, { "id": "emo_Sourness-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-0", "key": "fd1cc6cdea72ad4af93d0931147ee7beb7bf296e730880c2bef90f0f3326fb49", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] The door is still open.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] I put your coat on the chair.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "515a9c02145351de0526a20fdf48c6cb386351879a86dd440b5af46083cb2e01", "generation_seconds_batch": 23.643025108030997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08505585789680481, "target_z": -0.3007812572698118, "ce": 6.165581703186035, "genuineness": 3.9801597595214844, "identity": 0.28966012597084045, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fd1cc6cdea72ad4af93d0931147ee7beb7bf296e730880c2bef90f0f3326fb49.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "fd1fc3f20432b645ec1e6690d6e733e30047f383ae205c5a87f451fcf807cf61", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "921c68c474dc78d5ff5f6b8fb07149c9d428c4de31cf387e994a4f3d7db9ebc4", "generation_seconds_batch": 26.228021824965253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05803303420543671, "target_z": -0.36328125296177516, "ce": 5.982900142669678, "genuineness": 4.218649387359619, "identity": 0.6069607138633728, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fd1fc3f20432b645ec1e6690d6e733e30047f383ae205c5a87f451fcf807cf61.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "fdb1390bcc8945e6d6c81aa9625c658caa6b7d772c290cb5877a7bf0a5acc31f", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2d46c7b34c40f51c01327c9c92aa3242136c370cdeee535fcd0f03819c7f5263", "generation_seconds_batch": 23.384512135991827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0010793954133987427, "target_z": -0.5, "ce": 6.260893821716309, "genuineness": 3.9173994064331055, "identity": 0.4186267852783203, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fdb1390bcc8945e6d6c81aa9625c658caa6b7d772c290cb5877a7bf0a5acc31f.mp3" }, { "id": "emo_Sourness-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-1", "key": "fdc2c8437ea92abe66dd6aba39866daeae68726288462329a02dd759fe55bc4c", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cd229a552b3ffc2331aadbc96573671b6309363ba68519a614dbf92e397dac62", "generation_seconds_batch": 24.066893849987537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.024724364280700684, "target_z": -0.5546874919224314, "ce": 6.348263263702393, "genuineness": 4.15588903427124, "identity": 0.533597469329834, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fdc2c8437ea92abe66dd6aba39866daeae68726288462329a02dd759fe55bc4c.mp3" }, { "id": "emo_Sourness-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-de-0", "key": "fddf20472eedec720cebf70f1c655779e33753e13e0458431bfe971952c9f08a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Die Tür ist noch offen.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b2653b8f48b11f5f0fcbc349070dca790a0d846f925475e24e668f6566b54a3f", "generation_seconds_batch": 17.08024485502392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029321283102035522, "target_z": -0.4296875005385046, "ce": 6.24500846862793, "genuineness": 4.369274139404297, "identity": 0.5134121179580688, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/fddf20472eedec720cebf70f1c655779e33753e13e0458431bfe971952c9f08a.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": "fe50334f1f79abf4dc59388bd0e48e81fd2e9610dbf03579c1cd056a907f683a", "bucket": "emo_Sourness", "phase": "heldout", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7f793b108acb92b44413ab1b61b81b2437a8f55a5176acf2fa01e8848987c6a9", "generation_seconds_batch": 15.474634955986403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1323457956314087, "target_z": -0.19140627342494906, "ce": 6.205295085906982, "genuineness": 4.632867813110352, "identity": 0.7199803590774536, "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_Sourness/fe50334f1f79abf4dc59388bd0e48e81fd2e9610dbf03579c1cd056a907f683a.mp3" }, { "id": "emo_Sourness-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-nl-1", "key": "ff056423f63f40847d831f29f08343200e51f5d7f16e518cd147d77545da43cc", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] Het stond naast het oude raam.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d16acb196242cec241cac7d936212e7b9cf4a28a922b285c36870b75c31cb7c3", "generation_seconds_batch": 24.609106983989477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11545653641223907, "target_z": -0.23046875780831635, "ce": 6.046441555023193, "genuineness": 4.20609712600708, "identity": 0.48100483417510986, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ff056423f63f40847d831f29f08343200e51f5d7f16e518cd147d77545da43cc.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "ff2efb78a9cc2b74b2caf7e02a76193a60d692645a63e431c8df4f3366567749", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6c2c01ba36693538e8647aede1efb72ec60ae045e339f85b34a2a3d770c164cd", "generation_seconds_batch": 24.111863664002158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04621054232120514, "target_z": -0.3906250161551373, "ce": 6.062326908111572, "genuineness": 4.093128204345703, "identity": 0.5528018474578857, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ff2efb78a9cc2b74b2caf7e02a76193a60d692645a63e431c8df4f3366567749.mp3" }, { "id": "emo_Sourness-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-es-0", "key": "ff4676ab0f69a6b913f5bc0e5d99894b95139030eb0112e00e17dd4172fec71a", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] La puerta sigue abierta.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "303d73bdc2990804921b323fda18d6164dc025ee08ab1d859e29cbcbbda8f5fc", "generation_seconds_batch": 24.569044049014337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04114377498626709, "target_z": -0.40234373734514245, "ce": 5.974957466125488, "genuineness": 4.2374773025512695, "identity": 0.5040994882583618, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ff4676ab0f69a6b913f5bc0e5d99894b95139030eb0112e00e17dd4172fec71a.mp3" }, { "id": "emo_Sourness-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Sourness-en-1", "key": "ff94a5c0c8a78797e4bcd8681b56365f1b390df62b05e7188130c8645744c108", "bucket": "emo_Sourness", "phase": "grid", "candidate": "manual-909f760b761b", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Employ sharp, percussive articulation on consonants, giving the sourness a clipped, impatient edge.\nSCRIPT:\n(Attack the first consonant with sudden, sharp precision, immediately conveying annoyance.) [3.2 seconds duration] I found the little box.\n(Keep the vowel shapes tight and unrelaxed, resisting any tendency toward openness.) [3.8 seconds duration] It was beside the old window.\n(Finish the utterance with a sudden, abrupt cessation of vocal energy.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e72906355df87558816453d1d854f37848607d313ac5e054577fb82251deeaac", "generation_seconds_batch": 23.747901925002225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007835105061531067, "target_z": -0.515625007539064, "ce": 6.260893821716309, "genuineness": 4.111956596374512, "identity": 0.35310885310173035, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Sourness/ff94a5c0c8a78797e4bcd8681b56365f1b390df62b05e7188130c8645744c108.mp3" }, { "key": "original-emo_Sourness-de-0-seed1701-scale0.0", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "e146f906272ab271bf6c352f56fb00d27d210849c52dd6861bbc83a58f403eb6", "task_id": "emo_Sourness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.10110066086053848, "target_z": -0.26367188159668103, "ce": 6.300607204437256, "genuineness": 4.532451152801514, "identity": 0.49088290333747864, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/8c8d2c085f785f6e3a351065.mp3" }, { "key": "original-emo_Sourness-de-0-seed1701-scale0.5", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "3ffaea0e0c3dfb128a804a2a342f738df21d6959405fd9e4940d87ea1bdc660e", "task_id": "emo_Sourness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.11038976162672043, "target_z": -0.24218749623046795, "ce": 6.165581703186035, "genuineness": 4.344170093536377, "identity": 0.49449384212493896, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/52d26dbc6844b5c349688074.mp3" }, { "key": "original-emo_Sourness-de-0-seed1701-scale0.75", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "b2f6a808a251e577d3d3a91bf714ee3c2d0dd3535bd546f76018306d11539f78", "task_id": "emo_Sourness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.13994598388671875, "target_z": -0.1738281054792091, "ce": 6.09409761428833, "genuineness": 4.632867813110352, "identity": 0.5940940380096436, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/748810e8166100843edccd91.mp3" }, { "key": "original-emo_Sourness-de-0-seed1701-scale1.0", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "ccc945b580b1eea4b7bc809857d32dd7e93cd7d1a24ebb5e08f3df99f88fcbfc", "task_id": "emo_Sourness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.17372450232505798, "target_z": -0.09570313671247453, "ce": 6.24500846862793, "genuineness": 4.6705241203308105, "identity": 0.6408472061157227, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/14447f400429dd0beec4ca71.mp3" }, { "key": "original-emo_Sourness-de-0-seed1702-scale0.0", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "c0a769a5023b41f9b7256164e7435d0da8285251f8327e2d0cfb513b20e09aa6", "task_id": "emo_Sourness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.09012264013290405, "target_z": -0.2890625016155137, "ce": 6.022613525390625, "genuineness": 4.369274139404297, "identity": 0.5284491777420044, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/a8fd3be5f199eeeaaa86fef7.mp3" }, { "key": "original-emo_Sourness-de-0-seed1702-scale0.5", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "20d4860cefa5cd422dfa2ffddc0ad49486b05f0be2aa7b86d92cac9bc72046df", "task_id": "emo_Sourness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.07914461195468903, "target_z": -0.31445313886649284, "ce": 6.157639026641846, "genuineness": 4.111956596374512, "identity": 0.493275910615921, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/1bb9c3a501e1cf9cbce16c48.mp3" }, { "key": "original-emo_Sourness-de-0-seed1702-scale0.75", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "56730befc83312cd6532862c4c45ad24c4852524e05cec60acd8a4dc3b3bdb24", "task_id": "emo_Sourness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.10701190680265427, "target_z": -0.25, "ce": 6.149696350097656, "genuineness": 4.6203155517578125, "identity": 0.5423433780670166, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/ba9c88f6b5f739f3d67b4aea.mp3" }, { "key": "original-emo_Sourness-de-0-seed1702-scale1.0", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "2ebd0bc98de3bc86f14bc6c9b7d80090e51731681d24ba44920f60593068f652", "task_id": "emo_Sourness-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.11376761645078659, "target_z": -0.23437499246093593, "ce": 6.205295085906982, "genuineness": 4.6203155517578125, "identity": 0.47514790296554565, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/e00cfdb39940e9b1eb9fca17.mp3" }, { "key": "original-emo_Sourness-de-1-seed1701-scale0.0", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "d4d810716b2c3b4c534cbaeff9c4674a940a29a3d02fc569f893f0ae9c85c409", "task_id": "emo_Sourness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.019187718629837036, "target_z": -0.4531250118471007, "ce": 6.324435234069824, "genuineness": 4.306513786315918, "identity": 0.5598440170288086, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/5e9fa4187442ebc4df37318c.mp3" }, { "key": "original-emo_Sourness-de-1-seed1701-scale0.5", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "f6f787db9854deae089aad0aecda9f40ec1197a935600ae519b724b6686eb162", "task_id": "emo_Sourness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.043302565813064575, "target_z": -0.5976562626548575, "ce": 6.38003396987915, "genuineness": 4.344170093536377, "identity": 0.6033751964569092, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/fe2958a732d080c1cc7eb49b.mp3" }, { "key": "original-emo_Sourness-de-1-seed1701-scale0.75", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "11e6218c0db0836004efe7788749228eea57f3f55583766e20c0c3da13267a71", "task_id": "emo_Sourness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.021721109747886658, "target_z": -0.4472656340199517, "ce": 6.308549880981445, "genuineness": 4.250029563903809, "identity": 0.4221254587173462, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/aaed84e969c4aa82bea36ccd.mp3" }, { "key": "original-emo_Sourness-de-1-seed1701-scale1.0", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "ed60842075398cfb02a21eaae823203dedee39eff317fa2dabe63624f2baf8af", "task_id": "emo_Sourness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.02134650945663452, "target_z": -0.5468749881528994, "ce": 6.356205940246582, "genuineness": 4.394378662109375, "identity": 0.5695379972457886, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/f6d4cc4104aea1e164f3b01e.mp3" }, { "key": "original-emo_Sourness-de-1-seed1702-scale0.0", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "ad5d7b0e50cda55aa5b3c4906586bf1c6c4750c22a181254035eeb12c6ca4410", "task_id": "emo_Sourness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.009898632764816284, "target_z": -0.4746093627490209, "ce": 6.292664527893066, "genuineness": 4.344170093536377, "identity": 0.459502637386322, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/8551229b2130b675c52aceea.mp3" }, { "key": "original-emo_Sourness-de-1-seed1702-scale0.5", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "72491b1938e5caf861cd636ddfae314f4373b480915db89c6e652f594b6c19ec", "task_id": "emo_Sourness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.04705500602722168, "target_z": -0.3886718902127543, "ce": 6.300607204437256, "genuineness": 4.432034492492676, "identity": 0.4219093918800354, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/1598755b651f61f1a0458bb5.mp3" }, { "key": "original-emo_Sourness-de-1-seed1702-scale0.75", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "53578c79b42d9c74df14fdd79ea44611ad366421dd6623ae9e12249ab3c24157", "task_id": "emo_Sourness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.04874393343925476, "target_z": -0.38476563832798827, "ce": 6.316492557525635, "genuineness": 4.557555198669434, "identity": 0.5435965657234192, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/d96bf948a379f18d5c81d554.mp3" }, { "key": "original-emo_Sourness-de-1-seed1702-scale1.0", "bucket": "emo_Sourness", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "d5cddce22a9bca13bb29911b86b6d2d297da8c257296bdef4b8d464be7963228", "task_id": "emo_Sourness-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.05127732455730438, "target_z": -0.37890626050083925, "ce": 6.348263263702393, "genuineness": 4.400654315948486, "identity": 0.44718989729881287, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/de/503b972d6e4350a6f1bbeee1.mp3" }, { "key": "original-emo_Sourness-en-0-seed1701-scale0.0", "bucket": "emo_Sourness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "9519dabffbcf7eaa6ee1cf56549fdb5b7bb94bc3cc286548f6be68c7a2db7e0a", "task_id": "emo_Sourness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.08843371272087097, "target_z": -0.29296875350027973, "ce": 6.340320587158203, "genuineness": 4.18099308013916, "identity": 0.44951730966567993, "hypothesis": "The 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_Sourness/en/7b82fb093e908da33b7660e9.mp3" }, { "key": "original-emo_Sourness-en-0-seed1701-scale0.5", "bucket": "emo_Sourness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "bd6a95c88024004cd884707fc4200e03acbf8cd08dcfad4635eb7fff19b27f32", "task_id": "emo_Sourness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.08843371272087097, "target_z": -0.29296875350027973, "ce": 6.252951145172119, "genuineness": 4.18099308013916, "identity": 0.422174334526062, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/9e7db5453aafe3eef88888b0.mp3" }, { "key": "original-emo_Sourness-en-0-seed1701-scale0.75", "bucket": "emo_Sourness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "a16306b7359254dd041a167926c6f43dac9daa90d492a2874809a9ad951954b3", "task_id": "emo_Sourness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.08421139419078827, "target_z": -0.3027343832121948, "ce": 6.141753673553467, "genuineness": 3.9801597595214844, "identity": 0.2693102955818176, "hypothesis": "The 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_Sourness/en/1e3179c2c88ee1ca864c9b96.mp3" }, { "key": "original-emo_Sourness-en-0-seed1701-scale1.0", "bucket": "emo_Sourness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "15b57b4cca617dca1290cf98be6e988abd7f8379fdb3e520530d17853e3642bc", "task_id": "emo_Sourness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.08590032160282135, "target_z": -0.29882813132742875, "ce": 6.23706579208374, "genuineness": 3.9927117824554443, "identity": 0.3017929196357727, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/7a6344ee807ba41a6026f9f1.mp3" }, { "key": "original-emo_Sourness-en-0-seed1702-scale0.0", "bucket": "emo_Sourness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "ddccf57dfb30c17168b16e7340595ffd9eb13c7828d4d4984706d20b71db4ba9", "task_id": "emo_Sourness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.0723889172077179, "target_z": -0.330078111941264, "ce": 6.125868320465088, "genuineness": 3.9299514293670654, "identity": 0.5749638080596924, "hypothesis": "The 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_Sourness/en/9a077b72f79b0ce611feaeb0.mp3" }, { "key": "original-emo_Sourness-en-0-seed1702-scale0.5", "bucket": "emo_Sourness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "d9f7f8d4d8baa030d45124a99e11dbd1340e2fa543976b434347b8d16dbd15b1", "task_id": "emo_Sourness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.10701190680265427, "target_z": -0.25, "ce": 6.109982967376709, "genuineness": 3.9801597595214844, "identity": 0.17102134227752686, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/749a17a4b28184f29a4dcd0a.mp3" }, { "key": "original-emo_Sourness-en-0-seed1702-scale0.75", "bucket": "emo_Sourness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "a7273c4643c3ffa7886e09ce17b96bbb64f9498adcee793bba3c38f9f7686f4c", "task_id": "emo_Sourness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.12390117347240448, "target_z": -0.21093749838448628, "ce": 6.173524379730225, "genuineness": 4.105680465698242, "identity": 0.6018364429473877, "hypothesis": "The 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_Sourness/en/282885da2768d433d96e83cf.mp3" }, { "key": "original-emo_Sourness-en-0-seed1702-scale1.0", "bucket": "emo_Sourness", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "b6777142bd01b893b20e35b560d52499128b0bb44538a819eb53a205aff5f46b", "task_id": "emo_Sourness-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.09181156754493713, "target_z": -0.2851562497307477, "ce": 6.221180438995361, "genuineness": 4.15588903427124, "identity": 0.3507175147533417, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/0c877a7a83ff57d2ade81e05.mp3" }, { "key": "original-emo_Sourness-en-1-seed1701-scale0.0", "bucket": "emo_Sourness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "c890c58346e4bdcc1373f65c201463290287c31ad973da28b8bb55f6eaea21c6", "task_id": "emo_Sourness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.014965400099754333, "target_z": -0.4628906415590157, "ce": 6.23706579208374, "genuineness": 4.2249250411987305, "identity": 0.30362212657928467, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/78209428f88c410cf17f0108.mp3" }, { "key": "original-emo_Sourness-en-1-seed1701-scale0.5", "bucket": "emo_Sourness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "1ee78cd4b73031bbb8d1f6c2c0b503b115f0c846e672cd71881c9dd1de55efdb", "task_id": "emo_Sourness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.014590814709663391, "target_z": -0.5312500150781282, "ce": 6.372091293334961, "genuineness": 4.256305694580078, "identity": 0.45996809005737305, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/743efc2f9af6eeae33507b61.mp3" }, { "key": "original-emo_Sourness-en-1-seed1701-scale0.75", "bucket": "emo_Sourness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "eeef4bfa7674d4a9ab14ecfc84fab48cf262a5db40ab3d826f70ac3929f20b5f", "task_id": "emo_Sourness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.014120951294898987, "target_z": -0.46484373303710586, "ce": 6.252951145172119, "genuineness": 4.356721878051758, "identity": 0.532515287399292, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/3c2e13492a49be8a5d7aa293.mp3" }, { "key": "original-emo_Sourness-en-1-seed1701-scale1.0", "bucket": "emo_Sourness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "944ae2028c0a060308113b0fcbab0b9aafc34c69e862eb536df5bc504b84b582", "task_id": "emo_Sourness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.03654685616493225, "target_z": -0.5820312551157935, "ce": 6.372091293334961, "genuineness": 4.1998209953308105, "identity": 0.33195552229881287, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/334a03bd95bfe0bcb38a041c.mp3" }, { "key": "original-emo_Sourness-en-1-seed1702-scale0.0", "bucket": "emo_Sourness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "959bd4238eafe7cc1a833a1b2a4fa5b04d398ad7940d12d882b16613b7f7442d", "task_id": "emo_Sourness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.02134650945663452, "target_z": -0.5468749881528994, "ce": 6.300607204437256, "genuineness": 4.444586753845215, "identity": 0.4807441532611847, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/c4b19579f16dfa5910ce1fc6.mp3" }, { "key": "original-emo_Sourness-en-1-seed1702-scale0.5", "bucket": "emo_Sourness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "7b2a61d3fe28c8bb88ffc0a73bdbc4f219c5f8679128bc96acf71cb6ed9a74c8", "task_id": "emo_Sourness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.021721109747886658, "target_z": -0.4472656340199517, "ce": 6.348263263702393, "genuineness": 4.469690799713135, "identity": 0.5661832094192505, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/1d6ed9bc1b0ca25ddf1206b3.mp3" }, { "key": "original-emo_Sourness-en-1-seed1702-scale0.75", "bucket": "emo_Sourness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "7b5e3ba6424335818e05eafa53a613cb57fe92a5f325a5844fa250c2b907d9c0", "task_id": "emo_Sourness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.435632705688477, "genuineness": 4.607763767242432, "identity": 0.5943551063537598, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/e3fff0b7e88b8d12c55febc2.mp3" }, { "key": "original-emo_Sourness-en-1-seed1702-scale1.0", "bucket": "emo_Sourness", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "978fa2e88bd0f887d7678bae8c1a14d947fc862581913677538bbdff77457058", "task_id": "emo_Sourness-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.043302565813064575, "target_z": -0.5976562626548575, "ce": 6.38003396987915, "genuineness": 4.482243061065674, "identity": 0.368554025888443, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/en/d935e37af17b843f575880d5.mp3" }, { "key": "original-emo_Sourness-es-0-seed1701-scale0.0", "bucket": "emo_Sourness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "c66110a7a68a8d65958f24f4be8d6287bc47565f3310e44bdd74aaccdc2d5da7", "task_id": "emo_Sourness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.1306568682193756, "target_z": -0.1953125253097151, "ce": 5.903473377227783, "genuineness": 4.557555198669434, "identity": 0.6208699345588684, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/a5d3d333768a3ecfbac5c960.mp3" }, { "key": "original-emo_Sourness-es-0-seed1701-scale0.5", "bucket": "emo_Sourness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "85eca3ea491cb21f5d081f80df537d685f915325e0bff2828b974ebb37f0b426", "task_id": "emo_Sourness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.08843371272087097, "target_z": -0.29296875350027973, "ce": 6.054384231567383, "genuineness": 4.337893962860107, "identity": 0.5912984609603882, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/77a7236dc34e03d9a0b19713.mp3" }, { "key": "original-emo_Sourness-es-0-seed1701-scale0.75", "bucket": "emo_Sourness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "a7d8f7ea3ff3059a35dd95899de62bfe9bc530239bda305383bfac62e5ab91ba", "task_id": "emo_Sourness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.1433238387107849, "target_z": -0.16601560170967708, "ce": 5.847874641418457, "genuineness": 4.406930446624756, "identity": 0.6246306896209717, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/aa377bd92ac67fc374ff7880.mp3" }, { "key": "original-emo_Sourness-es-0-seed1701-scale1.0", "bucket": "emo_Sourness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "25ce47d814336daaa30029a26ee06766a6bc76e51922057832b233f9aa61daf1", "task_id": "emo_Sourness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.03776592016220093, "target_z": -0.41015624111467447, "ce": 5.959072113037109, "genuineness": 4.055472373962402, "identity": 0.3573858439922333, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/80bc7eca1945432037a85534.mp3" }, { "key": "original-emo_Sourness-es-0-seed1702-scale0.0", "bucket": "emo_Sourness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "8ef2c094922a3acd0ff22217bc9b559a2c76ff3f098e7dce0cef856c83b8ed29", "task_id": "emo_Sourness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.06732213497161865, "target_z": -0.34179686759556205, "ce": 5.911416053771973, "genuineness": 4.042920112609863, "identity": 0.5666637420654297, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/10eac3ec5b23c2beca15fce6.mp3" }, { "key": "original-emo_Sourness-es-0-seed1702-scale0.5", "bucket": "emo_Sourness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "9a1f716f66adbe8b602a92a7fe374c72dbec4b156ae03318a6e4309f8efa4376", "task_id": "emo_Sourness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.11714546382427216, "target_z": -0.22656250592355034, "ce": 6.038498878479004, "genuineness": 4.457139015197754, "identity": 0.48416388034820557, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/c3adfc9835484b5c6b62c637.mp3" }, { "key": "original-emo_Sourness-es-0-seed1702-scale0.75", "bucket": "emo_Sourness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "eaddc76fa6da0bce2c9432e900dc0aa6e2e5fd88bcb93fcc14fede092bcc82a7", "task_id": "emo_Sourness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.08590032160282135, "target_z": -0.29882813132742875, "ce": 6.086154937744141, "genuineness": 3.9676074981689453, "identity": 0.5359306335449219, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/4141c883d4be407003f3ebdf.mp3" }, { "key": "original-emo_Sourness-es-0-seed1702-scale1.0", "bucket": "emo_Sourness", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "1e557ef0f39a037c9403d50d8f38a9305f0682ce1d289f4af518e943a82e678c", "task_id": "emo_Sourness-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.09012264013290405, "target_z": -0.2890625016155137, "ce": 6.173524379730225, "genuineness": 4.444586753845215, "identity": 0.5224456787109375, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/339f118760e26acd223d3ff1.mp3" }, { "key": "original-emo_Sourness-es-1-seed1701-scale0.0", "bucket": "emo_Sourness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "accaa2c2c3af5fbdebdfbf23fc5c921674d560edf78dee9591519efb44995d45", "task_id": "emo_Sourness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.5868687629699707, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/607f5ddd146b29c738765a08.mp3" }, { "key": "original-emo_Sourness-es-1-seed1701-scale0.5", "bucket": "emo_Sourness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "88eb6db7d5d3ecfa139ea83981ffa89a19dbc05a71f3345f7858db65c76bb197", "task_id": "emo_Sourness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.03945484757423401, "target_z": -0.40624998922990846, "ce": 6.062326908111572, "genuineness": 4.595211505889893, "identity": 0.595849335193634, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/f164fb281d3d0eeb3623cc10.mp3" }, { "key": "original-emo_Sourness-es-1-seed1701-scale0.75", "bucket": "emo_Sourness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "69a54990a43948c2ef8c66936b7cb74085f353363fd6b26f1a5b8f7bbc5282f4", "task_id": "emo_Sourness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.04367716610431671, "target_z": -0.39648435951799343, "ce": 6.070269584655762, "genuineness": 4.557555198669434, "identity": 0.5112669467926025, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/0fb51f697d2575409d0b8daf.mp3" }, { "key": "original-emo_Sourness-es-1-seed1701-scale1.0", "bucket": "emo_Sourness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "27a2385e7f826f8a2aecb05d4afc2167dd8aa2f594b280f97c356809894f2075", "task_id": "emo_Sourness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.004457250237464905, "target_z": -0.507812503769532, "ce": 6.149696350097656, "genuineness": 4.356721878051758, "identity": 0.32712000608444214, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/7078847cc2bcc1d470a15bf0.mp3" }, { "key": "original-emo_Sourness-es-1-seed1702-scale0.0", "bucket": "emo_Sourness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "66c483bab650bffaefc0322dfcf943898b0c4d1bfd18da523fe0ecab45d335a1", "task_id": "emo_Sourness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.03148007392883301, "target_z": -0.5703124994614954, "ce": 6.221180438995361, "genuineness": 4.607763767242432, "identity": 0.5728583335876465, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/bdceb8381ad25739e4dc3be9.mp3" }, { "key": "original-emo_Sourness-es-1-seed1702-scale0.5", "bucket": "emo_Sourness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "01f248e05d370b344fb1a31bf022296c02b45552f1c6b0be9e6de0b10e60c6cd", "task_id": "emo_Sourness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.07069998979568481, "target_z": -0.33398436382603003, "ce": 6.062326908111572, "genuineness": 4.65797233581543, "identity": 0.662319004535675, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/dec0e7dd3d74412986762cea.mp3" }, { "key": "original-emo_Sourness-es-1-seed1702-scale0.75", "bucket": "emo_Sourness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "face2784cdac0398b0d3523a1acc461441e7bf793b151bdab1b3c90eaa75bd89", "task_id": "emo_Sourness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.03607699275016785, "target_z": -0.4140624929994405, "ce": 6.268836498260498, "genuineness": 4.65797233581543, "identity": 0.6004290580749512, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/74ababa78b2367dfb0277797.mp3" }, { "key": "original-emo_Sourness-es-1-seed1702-scale1.0", "bucket": "emo_Sourness", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "36d40fe8f60db20b10b5fe6efde40ba6f215c4fb565bc124ef94b3b26ead8888", "task_id": "emo_Sourness-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.007835105061531067, "target_z": -0.515625007539064, "ce": 6.125868320465088, "genuineness": 4.532451152801514, "identity": 0.5951011180877686, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/es/c9bee13bde5aecc01c2a8e80.mp3" }, { "key": "original-emo_Sourness-fr-0-seed1701-scale0.0", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "1b2ed7b6e9429a1f3450fb286faf86bcf36e59c005d13804edf09a19e0e67ee2", "task_id": "emo_Sourness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.06732213497161865, "target_z": -0.34179686759556205, "ce": 6.062326908111572, "genuineness": 4.425758361816406, "identity": 0.6329063177108765, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/fr/f91327a6d908b4b4813a3716.mp3" }, { "key": "original-emo_Sourness-fr-0-seed1701-scale0.5", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "043d49161f4ab724e37ab4205ef9b05a434db32e5089707268cf39ce55037de1", "task_id": "emo_Sourness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.0022984594106674194, "target_z": -0.492187496230468, "ce": 6.173524379730225, "genuineness": 4.632867813110352, "identity": 0.610959529876709, "hypothesis": "Ma porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/fr/0c16c270f4ced2057dc71a1e.mp3" }, { "key": "original-emo_Sourness-fr-0-seed1701-scale0.75", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "09c7cb331b6b9a352955b3794106c8b336c1c51ec4ab68291fd6bcd3b3b31bc3", "task_id": "emo_Sourness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.05803303420543671, "target_z": -0.36328125296177516, "ce": 6.1894097328186035, "genuineness": 4.632867813110352, "identity": 0.7507932186126709, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/fr/85feb331241655922a048d1a.mp3" }, { "key": "original-emo_Sourness-fr-0-seed1701-scale1.0", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "2f2413989e055d88c7e8770bfbead8d5690e1f7c2fec9001de7446a0127416db", "task_id": "emo_Sourness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.05296625196933746, "target_z": -0.37500000861607324, "ce": 6.0146708488464355, "genuineness": 4.15588903427124, "identity": 0.8262108564376831, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/fr/e708f60fa82233e465d28ef0.mp3" }, { "key": "original-emo_Sourness-fr-0-seed1702-scale0.0", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "2632a1ffd6c8458b36f48a38c2f33af1a039a6fd5165a145e1698b9b97f9ed20", "task_id": "emo_Sourness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.04367716610431671, "target_z": -0.39648435951799343, "ce": 6.268836498260498, "genuineness": 4.632867813110352, "identity": 0.750908374786377, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/fr/c946922f5dd0e256fb610fc1.mp3" }, { "key": "original-emo_Sourness-fr-0-seed1702-scale0.5", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "a218c97226ede3773a7f1002abfb93e413af1bce9d25f8c1f12c15205ffd89b6", "task_id": "emo_Sourness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.11883439123630524, "target_z": -0.22265625403878433, "ce": 6.117925643920898, "genuineness": 4.645420074462891, "identity": 0.7214362621307373, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/fr/2733d5b7ecb31ff7466a49e4.mp3" }, { "key": "original-emo_Sourness-fr-0-seed1702-scale0.75", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "a355612182bb428e3b1f7815240eee84669ef58db00c59f8760ab7eacd95e8f5", "task_id": "emo_Sourness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.09772281348705292, "target_z": -0.2714843681340667, "ce": 6.1020402908325195, "genuineness": 4.68307638168335, "identity": 0.5811824798583984, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/fr/16eb3384f394caee5c57a957.mp3" }, { "key": "original-emo_Sourness-fr-0-seed1702-scale1.0", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "36538504c87136520758ea0637c107b66bdcfb840d94dd52c93df1aacc99b169", "task_id": "emo_Sourness-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.009054169058799744, "target_z": -0.4765624886914039, "ce": 6.173524379730225, "genuineness": 4.3881025314331055, "identity": 0.7122048139572144, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/fr/3b60a496de5814bc94e01342.mp3" }, { "key": "original-emo_Sourness-fr-1-seed1701-scale0.0", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "f424dcc8492e816619caf954a71e79545d5045bc6a2b8773187a71f1045190f5", "task_id": "emo_Sourness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.018343254923820496, "target_z": -0.4550781377894837, "ce": 6.0146708488464355, "genuineness": 4.68307638168335, "identity": 0.7963396906852722, "hypothesis": "J'ai trouvé la 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_Sourness/fr/f3676fe7f443d19e5d76fc30.mp3" }, { "key": "original-emo_Sourness-fr-1-seed1701-scale0.5", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "f083551aac4b4b8fd12fe41eafdb81f225220b9618a025f60116d2e62564b9db", "task_id": "emo_Sourness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.0056763142347335815, "target_z": -0.4843749924609359, "ce": 6.09409761428833, "genuineness": 4.545003414154053, "identity": 0.6608465313911438, "hypothesis": "J'ai trouvé la 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_Sourness/fr/ab2d7be020640a85a5c4a297.mp3" }, { "key": "original-emo_Sourness-fr-1-seed1701-scale0.75", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "91328d86273d37ad61772a1e542720d670d383153fa9314a4743b7658b96ccaf", "task_id": "emo_Sourness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.02594342827796936, "target_z": -0.4375000043080366, "ce": 6.252951145172119, "genuineness": 4.7834930419921875, "identity": 0.8041887879371643, "hypothesis": "J'ai trouvé la 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_Sourness/fr/cc9d0ee2f3ac2ca12b9f6ea3.mp3" }, { "key": "original-emo_Sourness-fr-1-seed1701-scale1.0", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "091fec4f4e76cce006a74182aaef5ba7a74d7c303d19b6e9cde963618cb42803", "task_id": "emo_Sourness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.04705500602722168, "target_z": -0.3886718902127543, "ce": 6.133810997009277, "genuineness": 4.582659721374512, "identity": 0.6103367805480957, "hypothesis": "J'ai trouvé la 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_Sourness/fr/7e08f4bd4edb8a3fcd1e2db3.mp3" }, { "key": "original-emo_Sourness-fr-1-seed1702-scale0.0", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "7fecfd330b68a0ec6929e96edbfce902078d1557041908c77be8bc00228345bf", "task_id": "emo_Sourness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.04836934804916382, "target_z": -0.6093750183091556, "ce": 6.24500846862793, "genuineness": 4.482243061065674, "identity": 0.741025447845459, "hypothesis": "J'ai trouvé la 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_Sourness/fr/b1d5816a7bb4e68be7b90b1e.mp3" }, { "key": "original-emo_Sourness-fr-1-seed1702-scale0.5", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "3e2c2966ef07d81e4d69fed13764a0b79d55e100a435e7d25ab1934c348faeee", "task_id": "emo_Sourness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.00023493170738220215, "target_z": -0.498046874057617, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.6875600814819336, "hypothesis": "J'ai trouvé la 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_Sourness/fr/0449af9b7e398bba155e6df7.mp3" }, { "key": "original-emo_Sourness-fr-1-seed1702-scale0.75", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "1ccb6277a874b4c937c3a781bdab4fef34202dfe105068f4cdd63d705c45d400", "task_id": "emo_Sourness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.009898632764816284, "target_z": -0.4746093627490209, "ce": 6.205295085906982, "genuineness": 4.645420074462891, "identity": 0.7392193078994751, "hypothesis": "J'ai trouvé la 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_Sourness/fr/677ec90d86a244a7836f29b9.mp3" }, { "key": "original-emo_Sourness-fr-1-seed1702-scale1.0", "bucket": "emo_Sourness", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "b277dc9624a0de3b53da4fb62d0f405d9c688b57b28e33683744d9fd7b5f3e9a", "task_id": "emo_Sourness-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": -0.00023493170738220215, "target_z": -0.498046874057617, "ce": 6.165581703186035, "genuineness": 4.394378662109375, "identity": 0.7401353716850281, "hypothesis": "J'ai trouvé la 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_Sourness/fr/6247c029efa43a8b9dd14f1d.mp3" }, { "key": "original-emo_Sourness-nl-0-seed1701-scale0.0", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "3b697ff04712343716e3bb765297d41b58023af17cdf47c2f1edd89e5f886461", "task_id": "emo_Sourness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.159368634223938, "target_z": -0.1289062432686928, "ce": 6.173524379730225, "genuineness": 4.406930446624756, "identity": 0.6943625211715698, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/7ba5f6676b17ee27347e27d7.mp3" }, { "key": "original-emo_Sourness-nl-0-seed1701-scale0.5", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "4ba04eb29ad644cba59b5e9b470057e48b44c932bf098e66d381f5ec2ba3120f", "task_id": "emo_Sourness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.20834749937057495, "target_z": -0.01562500753906407, "ce": 6.141753673553467, "genuineness": 4.15588903427124, "identity": 0.4855196475982666, "hypothesis": "De deur staat nog open. Ik heb jouw jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/85b13a9127f21300fb0f59bb.mp3" }, { "key": "original-emo_Sourness-nl-0-seed1701-scale0.75", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "5714851a4444c8c57e61f57ea1a4829cecfe04f17ab909673c39560422646a5b", "task_id": "emo_Sourness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.2176366001367569, "target_z": 0.005859377827149026, "ce": 5.990842819213867, "genuineness": 4.268857479095459, "identity": 0.4399219751358032, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/4d7ea82e391abe4d9876581f.mp3" }, { "key": "original-emo_Sourness-nl-0-seed1701-scale1.0", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "0bd0e0cae0b95356d2b05a8049887bde2c3f070e64b05c1597ec3562d6545503", "task_id": "emo_Sourness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.5511996150016785, "target_z": 0.7773437804255086, "ce": 6.062326908111572, "genuineness": 4.168440818786621, "identity": 0.5814617872238159, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/e1eddc67eca17fbfbfc84ec6.mp3" }, { "key": "original-emo_Sourness-nl-0-seed1702-scale0.0", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "966deebcf9a27e90c42146735d4c01b1d55d518a97e66f6fbce5068845353e28", "task_id": "emo_Sourness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.13994598388671875, "target_z": -0.1738281054792091, "ce": 6.006728172302246, "genuineness": 4.413206577301025, "identity": 0.6066978573799133, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/d62a45ddceb14a6fddbb34df.mp3" }, { "key": "original-emo_Sourness-nl-0-seed1702-scale0.5", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "74031b64b7dbf096e402a479af80eb688ac80a695e5932be0d558ce82949b6b0", "task_id": "emo_Sourness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.13403472304344177, "target_z": -0.18750002154018305, "ce": 6.181467056274414, "genuineness": 4.482243061065674, "identity": 0.5798781514167786, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/e9dd2cdab924c64b0b40097a.mp3" }, { "key": "original-emo_Sourness-nl-0-seed1702-scale0.75", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "5ec774b979593949b1fe2b166ae435f1ad83d0cdceba7d18e610f37684d28eea", "task_id": "emo_Sourness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.17456896603107452, "target_z": -0.09375001077009153, "ce": 6.149696350097656, "genuineness": 4.306513786315918, "identity": 0.7727620601654053, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/7ece8c16bbecdcd95381897c.mp3" }, { "key": "original-emo_Sourness-nl-0-seed1702-scale1.0", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "badefe55fa8914a0b51479c37f5def5f7e4c5a9c498ce97d426d667cd01b33df", "task_id": "emo_Sourness-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.18723592162132263, "target_z": -0.0644531216343464, "ce": 6.046441555023193, "genuineness": 4.250029563903809, "identity": 0.6623472571372986, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd - zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/9b54dc09b4b8adb4f27f4d9a.mp3" }, { "key": "original-emo_Sourness-nl-1-seed1701-scale0.0", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "37a23a3935b80c0d0deddb7293b27a87fd8b57a9d1a39f658b58828306948859", "task_id": "emo_Sourness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.1264345645904541, "target_z": -0.20507812055733723, "ce": 6.054384231567383, "genuineness": 4.469690799713135, "identity": 0.6511038541793823, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken. Eh.", "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/audio/emo_Sourness/nl/b1153b177fdc8c221ae2303a.mp3" }, { "key": "original-emo_Sourness-nl-1-seed1701-scale0.5", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "69c9ea50266fecad0a59e5ad1f6bdcdcaed9e5930eb27fdd39b15f211b40bd7a", "task_id": "emo_Sourness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.11038976162672043, "target_z": -0.24218749623046795, "ce": 6.0305562019348145, "genuineness": 4.413206577301025, "identity": 0.6021808385848999, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/83dc0a81450961dfb8d7bdc8.mp3" }, { "key": "original-emo_Sourness-nl-1-seed1701-scale0.75", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "b098517ade83bf24b051b1867b1571c71b036342891329496667a08198020228", "task_id": "emo_Sourness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.10025619715452194, "target_z": -0.2656250075390641, "ce": 6.1894097328186035, "genuineness": 4.099404335021973, "identity": 0.7857701778411865, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/f06816818008c89cf6498391.mp3" }, { "key": "original-emo_Sourness-nl-1-seed1701-scale1.0", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "36de75a91e60a65747ee677941fffbd973847eb4b082ecdfbefbe1ff4aed43da", "task_id": "emo_Sourness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.159368634223938, "target_z": -0.1289062432686928, "ce": 6.149696350097656, "genuineness": 4.20609712600708, "identity": 0.660881757736206, "hypothesis": "ik heb het kleine doosje gevonden het stond naast het oude raam we kunnen er samen in kijken", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/0fd009f007028bb924ba91ea.mp3" }, { "key": "original-emo_Sourness-nl-1-seed1702-scale0.0", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "c215450f6fea8dd16c069589b3740ed7a8b84a02b8c9c21da21588e170ec58c6", "task_id": "emo_Sourness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.11123422533273697, "target_z": -0.24023437028808495, "ce": 6.181467056274414, "genuineness": 4.519899368286133, "identity": 0.6573309302330017, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/100d3bdd2919ac0830b1085b.mp3" }, { "key": "original-emo_Sourness-nl-1-seed1702-scale0.5", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "3c8a69fb715c7510e70f927ab2a72024a108c7b3865771b283d6691bed9196f3", "task_id": "emo_Sourness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.11883439123630524, "target_z": -0.22265625403878433, "ce": 6.109982967376709, "genuineness": 4.1998209953308105, "identity": 0.6578855514526367, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/21c853656b302d1dce738ac9.mp3" }, { "key": "original-emo_Sourness-nl-1-seed1702-scale0.75", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "08d6c5bc0ce46f38cf821153a837d55a29d6988192ba2e09bb32d9bc1fed32ec", "task_id": "emo_Sourness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.10870083421468735, "target_z": -0.246093748115234, "ce": 5.959072113037109, "genuineness": 4.243753433227539, "identity": 0.6504099369049072, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude draam. 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/audio/emo_Sourness/nl/763f46163f9ca5cb49c2f212.mp3" }, { "key": "original-emo_Sourness-nl-1-seed1702-scale1.0", "bucket": "emo_Sourness", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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 Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "4eb158d6e8c9c8c4e8015d2e75202cad31ab7dd2f55296ebc811ca9b04d664a4", "mp3_sha256": "dbcb139b18df3f7684e208cf5aaf3822b9b1acc7c0101722468648acae8c95c6", "task_id": "emo_Sourness-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Sourness. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Sourness. 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 Sourness. 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 Sourness. 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": 0.12812349200248718, "target_z": -0.20117186867257122, "ce": 6.062326908111572, "genuineness": 4.419482707977295, "identity": 0.5529348850250244, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Sourness/nl/062db5606436d6274fc6434b.mp3" } ], "source_standard_audio_unchanged": true }