{ "complete": true, "report": { "bucket": "emo_Disappointment", "label": "Intense Disappointment", "definition": { "id": "emo_Disappointment", "category": "emotion", "head": "emo_Disappointment", "pole": "high", "label": "Intense Disappointment", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_disappointment/full-v2-sealed/sealed-selected", "mission": "emotion_disappointment", "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": 6.135002427101135, "genuineness": 4.576258029937744, "wer": 0.010963583438833717, "identity": 0.6217961037158966, "voiceclap": 0.012821109425276518, "fitness": 0.6523879658474344, "steering_v2": 0.6327502939993483, "raw_target": 0.8457133691012859, "target_cdf": 0.6327502939993483, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.156209354400635, "genuineness": 4.617177801132202, "wer": 0.011474070845038587, "identity": 0.6217961037158966, "fitness": 0.6607993031810202, "steering_v2": 0.6456928706821585 }, "none": { "n": 50, "ce": 6.113795499801636, "genuineness": 4.535338258743286, "wer": 0.010453096032628846, "identity": null, "fitness": 0.6439766285138486, "steering_v2": 0.6198077173165382 } } } } ], "selected_wording": { "id": "manual-3a61628184eb", "general": "Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.", "inline": [ "Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.", "Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.", "Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion." ], "cfg": 3, "recipe": "P05", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": -0.002148451874695002, "target_raw": 0.4882553294301033, "ce": 5.6794902086257935, "genuineness": 4.615922594070435, "identity": 0.5573056511580944, "wer": 0.01152046783625731, "valid_fraction": 1, "identity_delta": 0.0389143817126751, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": -0.0034179675714741966, "target_raw": 0.48736496567726134, "ce": 5.750378656387329, "genuineness": 4.652323603630066, "identity": 0.5419107720255851, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.023519502580165864, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": -0.002148451874695002, "target_raw": 0.4882553294301033, "ce": 5.6794902086257935, "genuineness": 4.615922594070435, "identity": 0.5573056511580944, "wer": 0.01152046783625731, "valid_fraction": 1, "identity_delta": 0.0389143817126751, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": -0.08608398431690366, "target_raw": 0.42938787639141085, "ce": 5.800020170211792, "genuineness": 4.631612658500671, "identity": 0.5570095866918564, "wer": 0.01330409356725146, "valid_fraction": 0.95, "identity_delta": 0.03861831724643707, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.1311523482151189, "target_raw": 0.39777957275509834, "ce": 5.888581013679504, "genuineness": 4.669268989562989, "identity": 0.6069900259375572, "wer": 0.008888888888888889, "valid_fraction": 1, "identity_delta": 0.08859875649213791, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": -0.19521485007420183, "target_raw": 0.3528498962521553, "ce": 6.00930962562561, "genuineness": 4.681193399429321, "identity": 0.6128270134329796, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.09443574398756027, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": -0.23222656140446896, "target_raw": 0.32689205557107925, "ce": 6.051207256317139, "genuineness": 4.622198605537415, "identity": 0.5750825740396976, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.05669130459427833, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -0.34125976369122174, "target_raw": 0.25042257085442543, "ce": 6.144930768013, "genuineness": 4.671151757240295, "identity": 0.5586360812187194, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.04024481177330017, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -0.37963867331080964, "target_raw": 0.22350585758686065, "ce": 6.115940022468567, "genuineness": 4.553789830207824, "identity": 0.5920526757836342, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.07366140633821487, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.4486328091470111, "target_raw": 0.17511742264032365, "ce": 6.178289985656738, "genuineness": 4.540296339988709, "identity": 0.5900629304349423, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.07167166098952293, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": -0.0034179675714741966, "target_raw": 0.48736496567726134, "ce": 5.750378656387329, "genuineness": 4.652323603630066, "identity": 0.5419107720255851, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.023519502580165864, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": -0.015185562187535952, "target_raw": 0.4791118659079075, "ce": 5.64573392868042, "genuineness": 4.596466851234436, "identity": 0.5776733338832856, "wer": 0.027540204678362573, "valid_fraction": 0.95, "identity_delta": 0.05928206443786621, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": -0.06323242131893501, "target_raw": 0.44541462063789367, "ce": 5.717317199707031, "genuineness": 4.613098430633545, "identity": 0.598189427703619, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": 0.07979815825819969, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": -0.06987304651812247, "target_raw": 0.4407572761178017, "ce": 5.607410454750061, "genuineness": 4.550651812553406, "identity": 0.5202584907412529, "wer": 0.008388157894736842, "valid_fraction": 1, "identity_delta": 0.0018672212958335877, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": -0.11347656671613457, "target_raw": 0.41017632782459257, "ce": 5.89473659992218, "genuineness": 4.6228262424469, "identity": 0.5710902094841004, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": 0.05269894003868103, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": -0.13178711031284096, "target_raw": 0.3973343878984451, "ce": 5.557371616363525, "genuineness": 4.537785911560059, "identity": 0.5451082482933998, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.0267169788479805, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": -0.1444824138826032, "target_raw": 0.3884306475520134, "ce": 5.705303812026978, "genuineness": 4.61372594833374, "identity": 0.582196769118309, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0638054996728897, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": -0.14589843275269887, "target_raw": 0.3874375350773335, "ce": 5.905260682106018, "genuineness": 4.666130876541137, "identity": 0.5874912872910499, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.06910001784563065, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": -0.17392578149898433, "target_raw": 0.3677807986736298, "ce": 5.7513714075088505, "genuineness": 4.587680435180664, "identity": 0.6111275151371955, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.09273624569177627, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": -0.178515625730354, "target_raw": 0.3645617514848709, "ce": 5.918366003036499, "genuineness": 4.632867860794067, "identity": 0.6086760759353638, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.09028480648994446, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": -0.18911133731252158, "target_raw": 0.357130541652441, "ce": 6.086353516578674, "genuineness": 4.667386102676391, "identity": 0.6051036357879639, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": 0.08671236634254456, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": -0.21323242344360124, "target_raw": 0.3402134284377098, "ce": 5.92094738483429, "genuineness": 4.66581711769104, "identity": 0.6076364278793335, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.08924515843391419, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": -0.24067382854827335, "target_raw": 0.32096763849258425, "ce": 6.021422171592713, "genuineness": 4.645106196403503, "identity": 0.64417132884264, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": 0.12578005939722062, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": -0.2503906251991875, "target_raw": 0.3141528479754925, "ce": 5.947555375099182, "genuineness": 4.637261128425598, "identity": 0.5488916628062726, "wer": 0.008388157894736842, "valid_fraction": 1, "identity_delta": 0.030500393360853195, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.32431641200983735, "target_raw": 0.2623056426644325, "ce": 6.1149471521377565, "genuineness": 4.5286856412887575, "identity": 0.5665875643491745, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.04819629490375519, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.33901367277964306, "target_raw": 0.25199784711003304, "ce": 6.046441602706909, "genuineness": 4.569479942321777, "identity": 0.5694377437233925, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": 0.051046474277973174, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -0.3424316435381166, "target_raw": 0.24960068315267564, "ce": 6.1500934839248655, "genuineness": 4.589563250541687, "identity": 0.5713128760457039, "wer": 0.007894736842105263, "valid_fraction": 0.95, "identity_delta": 0.052921606600284575, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": -0.3484863304073563, "target_raw": 0.24535428136587142, "ce": 6.0277763366699215, "genuineness": 4.587366652488709, "identity": 0.5314395159482956, "wer": 0.007894736842105263, "valid_fraction": 1, "identity_delta": 0.013048246502876282, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -0.3685546900562391, "target_raw": 0.23127951249480247, "ce": 6.100451731681824, "genuineness": 4.55912446975708, "identity": 0.5548243932425976, "wer": 0.011019736842105263, "valid_fraction": 1, "identity_delta": 0.036433123797178266, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -0.3783203157865931, "target_raw": 0.22443047612905503, "ce": 6.135399556159973, "genuineness": 4.497305417060852, "identity": 0.572846083343029, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.05445481389760971, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.40942382323660775, "target_raw": 0.20261630266904831, "ce": 6.145327877998352, "genuineness": 4.538413500785827, "identity": 0.5796789437532425, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.061287674307823184, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.4141601578932965, "target_raw": 0.1992945156991482, "ce": 6.151682043075562, "genuineness": 4.4772221326828, "identity": 0.5558291722089053, "wer": 0.008333333333333333, "valid_fraction": 0.95, "identity_delta": 0.03743790276348591, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.4239257814989843, "target_raw": 0.19244548082351684, "ce": 6.153667688369751, "genuineness": 4.4951088428497314, "identity": 0.5508037738502025, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.03241250440478325, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.44121093354944874, "target_raw": 0.18032269030809403, "ce": 6.141555142402649, "genuineness": 4.462787222862244, "identity": 0.5852377787232399, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.06684650927782058, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.49101562785502023, "target_raw": 0.14539260268211365, "ce": 6.151284885406494, "genuineness": 4.347621917724609, "identity": 0.5183912694454194, "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": -0.49980468368224035, "target_raw": 0.13922847509384156, "ce": 6.191395401954651, "genuineness": 4.313103711605072, "identity": 0.5311672948300838, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.012776025384664536, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.48330077990548465, "target_raw": 0.1508033439517021, "ce": 6.136590933799743, "genuineness": 4.278585457801819, "identity": 0.5915882825851441, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.07319701313972474, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.4743652347152786, "target_raw": 0.15707021057605744, "ce": 6.140959429740906, "genuineness": 4.3134174108505245, "identity": 0.592485336959362, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.07409406751394272, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.45179687272926294, "target_raw": 0.17289833426475526, "ce": 6.229758520126342, "genuineness": 4.351575784683227, "identity": 0.5865230727195739, "wer": 0.009105966497270844, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": -0.027929688675206014, "target_raw": 0.4701738840341568, "ce": 5.678020820617676, "genuineness": 4.510987215042114, "identity": 0.5520411780476571, "wer": 0.026361283643892338, "valid_fraction": 0.96, "identity_delta": -0.03448189467191696, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": -0.13972656225433547, "target_raw": 0.3917661225795746, "ce": 5.760227479934692, "genuineness": 4.519899196624756, "identity": 0.5416708663105965, "wer": 0.020237674225088414, "valid_fraction": 0.98, "identity_delta": -0.04485220640897751, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": -0.08765624965474174, "target_raw": 0.4282851818203926, "ce": 5.786636810302735, "genuineness": 4.565086679458618, "identity": 0.5679738667607307, "wer": 0.01572557876905703, "valid_fraction": 1, "identity_delta": -0.01854920595884323, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": -0.05207031259959373, "ci95_z": [ -0.1308398406194371, 0.031035150563198027 ], "language_deltas": { "en": 0.039843744821126056, "de": -0.0917968803780614, "fr": -0.1931640521090542, "nl": 0.06904296279097516, "es": -0.08427733812295427 }, "languages_improved": 2, "clear_gain": false, "delta_ce": -0.02640933036804199, "delta_genuineness": -0.04518748283386231, "delta_wer": 0.004512095456031383, "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": -0.11179687357912946, "ci95_z": [ -0.1841406256241207, -0.04076171621699946 ], "language_deltas": { "en": 0.008984380643644697, "de": -0.1072265571551365, "fr": -0.05761718554132331, "nl": -0.17314453747460812, "es": -0.22998046836822403 }, "languages_improved": 1, "clear_gain": false, "delta_ce": 0.0822066593170166, "delta_genuineness": 0.008911981582641601, "delta_wer": -0.006123609418803927, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.42386718405405693, "ci95_z": [ 0.24988280638494498, 0.636953122808938 ], "language_deltas": { "en": 0.1300781180284389, "de": 0.4021484263787002, "fr": 0.3312500053116656, "nl": 0.798828119090772, "es": 0.45703125146070805 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.551737699508667, "delta_genuineness": 0.15941143035888672, "delta_wer": 0.017255317146621495, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 5.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793023646.418082, "example": { "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.", "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." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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.", "language": "fr", "seed": 1701, "scale": 0.0, "cfg": 5.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "006b4b830e5160cc40ff396925f832b447b08c72b545ba6c80ef356776dd3ebb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2b9ba86a4e626556d8fd6b4bd9ad306d93b4457f3afcb5ae2501a5206a3cb27c", "generation_seconds_batch": 16.69278168200981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21991011500358582, "target_z": -0.3847656246680209, "ce": 5.6254801750183105, "genuineness": 4.432034492492676, "identity": 0.4875357151031494, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/006b4b830e5160cc40ff396925f832b447b08c72b545ba6c80ef356776dd3ebb.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "01344174b9c46e6c09a006508585c14cfcb50ebadab237ee2736fc979da6edc4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d137b57cdd9835beafe8f363a681c05e6f9f8e06ccf81ae832a0daa5837d8d80", "generation_seconds_batch": 20.100321225007065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16100841760635376, "target_z": -0.46874998406500323, "ce": 6.109982967376709, "genuineness": 4.6956281661987305, "identity": 0.5601925849914551, "hypothesis": "J'ai trouvé la 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_Disappointment/01344174b9c46e6c09a006508585c14cfcb50ebadab237ee2736fc979da6edc4.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "018135820475dd7a77332895c9df34e0db3da7426d84239e39f96359e6acd568", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c0211e12f6af921da6c880093fb2b784581f76c45ee9bf7ff7e87c9ae3627b30", "generation_seconds_batch": 21.790112674003467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2842910587787628, "target_z": -0.292968740040627, "ce": 5.593709468841553, "genuineness": 4.570107460021973, "identity": 0.5545161962509155, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/018135820475dd7a77332895c9df34e0db3da7426d84239e39f96359e6acd568.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "018220cea00528ce8dc98483ee264c8f78643ad96c394b021d2b73ab110e85f2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c18db3bbb4b0ac5bae0165882089a02fd914d03e28cec37afc7eae1117ef741", "generation_seconds_batch": 19.442150990013033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26100432872772217, "target_z": -0.3261718766598955, "ce": 5.601652145385742, "genuineness": 4.770940780639648, "identity": 0.701712965965271, "hypothesis": "La porte 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_Disappointment/018220cea00528ce8dc98483ee264c8f78643ad96c394b021d2b73ab110e85f2.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "01ac11a27712777e32c0ac812cd8b0fb3aca2b8278d551c6d8225914a352d446", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3d1273d0d48c07e73a858c8e878f3f9a96500df543753fa09466c6705888fda2", "generation_seconds_batch": 19.426929025910795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39250582456588745, "target_z": -0.1386718660365643, "ce": 6.149696350097656, "genuineness": 4.444586753845215, "identity": 0.6005988121032715, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/01ac11a27712777e32c0ac812cd8b0fb3aca2b8278d551c6d8225914a352d446.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "fae719af49e31703bf4e9086554b6a8b59badb864653bf878292103ea4a9d30f", "generation_seconds_batch": 16.603685406967998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.062382280826568604, "target_z": -0.609375013279164, "ce": 5.959072113037109, "genuineness": 4.419482707977295, "identity": 0.40730708837509155, "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_Disappointment/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "028f548a7242c329e7566ad0c738bf2947c11ce035cf5a147908056d1f8cdc83", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c105219aa1152be9d6415854a505315f55c04125ddb7749b1951a3e8b308f67d", "generation_seconds_batch": 14.303154492983595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14731034636497498, "target_z": -0.488281233401045, "ce": 6.292664527893066, "genuineness": 4.7081804275512695, "identity": 0.42295902967453003, "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_Disappointment/028f548a7242c329e7566ad0c738bf2947c11ce035cf5a147908056d1f8cdc83.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "02ee5449a599024f67ed6552f07b2ca69a1d1a7b0944cbd8ba20fa688d3bb4b7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f03a47aa49be0db7bc0b86efcde7cd2c381c5820215c3fad2d35d393db494067", "generation_seconds_batch": 19.734681513975374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24593645334243774, "target_z": -0.347656246680209, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.7890917062759399, "hypothesis": "La porte 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_Disappointment/02ee5449a599024f67ed6552f07b2ca69a1d1a7b0944cbd8ba20fa688d3bb4b7.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "04139c5da1df90b156a788282789b0c9b8575743423e90919dfe192b27f4dbf8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8645876787c44fec3a85e6a4dbf40a378740d283b00155ce9fc332aca0b02fe", "generation_seconds_batch": 19.99937877501361, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24593645334243774, "target_z": -0.347656246680209, "ce": 6.3641486167907715, "genuineness": 4.770940780639648, "identity": 0.556521475315094, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/04139c5da1df90b156a788282789b0c9b8575743423e90919dfe192b27f4dbf8.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "043391eb78d679777a71d318b27fe16357f060411d7e2fad1cdb44f133bf0c36", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6819ac55558e29f33239a56c785111b4ebb10361f75516c5d4753ac1439fd3fb", "generation_seconds_batch": 19.39733100903686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1938837766647339, "target_z": -0.4218750026558328, "ce": 5.760505676269531, "genuineness": 4.532451152801514, "identity": 0.7875179052352905, "hypothesis": "J'ai trouvé la 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_Disappointment/043391eb78d679777a71d318b27fe16357f060411d7e2fad1cdb44f133bf0c36.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "04735f9574e9ce713db134950252b4a423a5abaf68b3f456150aacdc7fe8b087", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8647e92c170479ff0bdf62d477a271b7b71f43e72613980e2fcb05180d2730dd", "generation_seconds_batch": 19.522968112956733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14731034636497498, "target_z": -0.488281233401045, "ce": 6.070269584655762, "genuineness": 4.7332844734191895, "identity": 0.7791234254837036, "hypothesis": "J'ai trouvé la 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_Disappointment/04735f9574e9ce713db134950252b4a423a5abaf68b3f456150aacdc7fe8b087.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": "04a00a4e2cbe600cbfe731040447b2a3bf719778978fd399f4d52836163f8e3a", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4317ea46388fd9787fbfe2bc691ced58fbb8cc9b3c77dc8a0ba225235beb450", "generation_seconds_batch": 15.131064251996577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39798504114151, "target_z": -0.1308593832994775, "ce": 5.4825119972229, "genuineness": 4.319066047668457, "identity": 0.7052258253097534, "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_Disappointment/04a00a4e2cbe600cbfe731040447b2a3bf719778978fd399f4d52836163f8e3a.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "04e313dbcee27c8e79f76d2773b6bff3d8769b546d618d413d363f27a0d3e099", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a00bc914363f1b94a35bd80c745078593909f50ea8463c582ad984cd0dd2c572", "generation_seconds_batch": 14.194926377036609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1514197587966919, "target_z": -0.4824218713482299, "ce": 6.022613525390625, "genuineness": 4.871357440948486, "identity": 0.7135144472122192, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/04e313dbcee27c8e79f76d2773b6bff3d8769b546d618d413d363f27a0d3e099.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "054ab60b9e57a0d3929eabc0852adf01667ce1b056410e8d4de4843afc4dc8f3", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a3cd4a4dac1e8c597ef10e46b96ed32af195fa673e4fffa3dc627a27b5d1057d", "generation_seconds_batch": 19.17863205401227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0075492858886719, "target_z": 0.7382813183876945, "ce": 6.022613525390625, "genuineness": 4.770940780639648, "identity": 0.6275060176849365, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/054ab60b9e57a0d3929eabc0852adf01667ce1b056410e8d4de4843afc4dc8f3.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "0573535ea26e13298ab1e983b70f66f3017aebae7490d6dcc5c23727ce0df74e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "66a79a069bc5342cb31253e9efd86d37246abd4cb432d97a596b894069c1dcf9", "generation_seconds_batch": 19.316672618035227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1692272424697876, "target_z": -0.457031259959373, "ce": 6.332377910614014, "genuineness": 4.482243061065674, "identity": 0.3559836149215698, "hypothesis": "The 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_Disappointment/0573535ea26e13298ab1e983b70f66f3017aebae7490d6dcc5c23727ce0df74e.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "02a76fb4d4d136d30f0684520608a590aba2b57e1dcebc094e3339769d1890e0", "generation_seconds_batch": 14.962605006992817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1623782217502594, "target_z": -0.4667968633807315, "ce": 6.292664527893066, "genuineness": 4.557555198669434, "identity": 0.5276970267295837, "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_Disappointment/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "068d677e2add3b74f80a0914bdc1833750f6b93032f09091cd2c21065eb2cf21", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1ae301cb2ff4348249cdeaed6e59520f7b8a9946d5630f237d3840eead57ee93", "generation_seconds_batch": 22.48388595005963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18977436423301697, "target_z": -0.4277343647086479, "ce": 6.197352409362793, "genuineness": 4.419482707977295, "identity": 0.30749577283859253, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/068d677e2add3b74f80a0914bdc1833750f6b93032f09091cd2c21065eb2cf21.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "06962ecbb1e4466400bfe7ccf3408a9099a15fbe432923e49f2e1759a569d71c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a2fa9ea018dbeb683033c0c6bbc89b31201ba6dcf058a9d4aa93f8f9893d0cdc", "generation_seconds_batch": 20.959235907997936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23086857795715332, "target_z": -0.3691406167005225, "ce": 5.816103935241699, "genuineness": 4.8588056564331055, "identity": 0.6638929843902588, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/06962ecbb1e4466400bfe7ccf3408a9099a15fbe432923e49f2e1759a569d71c.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "06a26b6717345fc2e2d27f3aeee6abda381d6c604ab608b077e0811ba45a9d6f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4bbca872b9435f7f186113e85f03a3381bcb5301d4ee5cd12daa97c752725c4a", "generation_seconds_batch": 19.522968112956733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07334074378013611, "target_z": -0.5937500053116656, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.7463964819908142, "hypothesis": "J'ai trouvé la 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_Disappointment/06a26b6717345fc2e2d27f3aeee6abda381d6c604ab608b077e0811ba45a9d6f.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "078cd3844f29e2990470d36dc45625a60336c7161061ab3e415323da85b4a824", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d7934c8b609934f276a1e5a7b6b063a02578efbd0b1bdf96d9be7141d8be74c0", "generation_seconds_batch": 14.074640545994043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2048422396183014, "target_z": -0.4062499946883344, "ce": 5.772419452667236, "genuineness": 4.406930446624756, "identity": 0.4245913028717041, "hypothesis": "The door is still open. Put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/078cd3844f29e2990470d36dc45625a60336c7161061ab3e415323da85b4a824.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "07d15fe33a35d3ede433e0127bc0e60f61a2df2e3bdd7596d3d71abf8cb8a59d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "57012442426f3d4bf1a3f5ec2c7af2f07119531fc7fdb9780dff4bc2a6f80bc0", "generation_seconds_batch": 19.13963764999062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6383861899375916, "target_z": 0.21191404042338988, "ce": 5.9431867599487305, "genuineness": 4.381826400756836, "identity": 0.49788692593574524, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond... het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/07d15fe33a35d3ede433e0127bc0e60f61a2df2e3bdd7596d3d71abf8cb8a59d.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "08463a8f8ae3d3c73db8e3d09c89b8c5f2a504ad84cf7b90f1ab741b8c61fab6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "30fb4a2f368c7e07585c4d9986a1382a5cd6256fad8924c014c5b7d6c4716ab0", "generation_seconds_batch": 14.237055195029825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.240457221865654, "target_z": -0.3554687506639582, "ce": 5.681078910827637, "genuineness": 4.720732688903809, "identity": 0.6927906274795532, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/08463a8f8ae3d3c73db8e3d09c89b8c5f2a504ad84cf7b90f1ab741b8c61fab6.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "0867bded81c238a04ed6b3a011638690e95eef95e88f52d85343b6299a04d2e5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "050be845d2ae17f2b87ac266098f3e8699996dd6802ecebed3fea5aae8d230dd", "generation_seconds_batch": 14.106301838997751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28840047121047974, "target_z": -0.2871093779878119, "ce": 5.967014789581299, "genuineness": 4.7332844734191895, "identity": 0.6258124113082886, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0867bded81c238a04ed6b3a011638690e95eef95e88f52d85343b6299a04d2e5.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "08d5377e6839dcddfac3e215f97d060f2671ca66c344cc20aff5102a7016866e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a600f448a925d89de36af4106467d3e345f15c31dcb1b88488b5e68c7e87b13d", "generation_seconds_batch": 20.986890834057704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1555291712284088, "target_z": -0.47656250929541477, "ce": 6.165581703186035, "genuineness": 4.174716949462891, "identity": 0.5791120529174805, "hypothesis": "La porte 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_Disappointment/08d5377e6839dcddfac3e215f97d060f2671ca66c344cc20aff5102a7016866e.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "09cf9c3d0bfca0564592047537c44ef77b571ab0c4da4a388224c93efa805d90", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c25998050ce2c8d880dfb9b4668c5cc6f28b8f53624dcd26078c9c2500f77ca8", "generation_seconds_batch": 16.3869332219474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17470648884773254, "target_z": -0.44921873472896146, "ce": 6.006728172302246, "genuineness": 4.7834930419921875, "identity": 0.5387243032455444, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/09cf9c3d0bfca0564592047537c44ef77b571ab0c4da4a388224c93efa805d90.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "0a1da3d56245f4aeafbdc4620e8d799507aa117410c0d4d8d127da3a20565031", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7a81d7f64a0c1e28df0e98410ed1ec87a69dcfdd5dee00661810d474bfc1f212", "generation_seconds_batch": 21.5864803600125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1623782217502594, "target_z": -0.4667968633807315, "ce": 6.006728172302246, "genuineness": 4.758388519287109, "identity": 0.7457426190376282, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0a1da3d56245f4aeafbdc4620e8d799507aa117410c0d4d8d127da3a20565031.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "0a3c044fca6997a736d6082768f6b0e5a55eba4d33c6fe35559df41808731770", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3d1e6fb2a8c7f064e9f6916ebe1858e34b838ceea96fd4e211973090726c568c", "generation_seconds_batch": 20.013352900976315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02128806710243225, "target_z": -0.6679687612872893, "ce": 6.403861999511719, "genuineness": 4.432034492492676, "identity": 0.5855189561843872, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0a3c044fca6997a736d6082768f6b0e5a55eba4d33c6fe35559df41808731770.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "0a502cd0e043378eed4fd3d5e5a7b578d8264464a2ac1308e646c14718fbcddf", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "44ef26f5bc45dcf500cbe73a805eb4c763b114eedda5ae43b39d229901fddeec", "generation_seconds_batch": 22.70355949900113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9938511848449707, "target_z": 0.718750026558328, "ce": 6.078212261199951, "genuineness": 4.293961524963379, "identity": 0.5375690460205078, "hypothesis": "De deur 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_Disappointment/0a502cd0e043378eed4fd3d5e5a7b578d8264464a2ac1308e646c14718fbcddf.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": "0a57415a1d828b5172e78167d134e2aabf68fc4abfa2200d61834e54091c4a13", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb9c47981db82239aae7800ae680c2d86dae92f23b4aa1c575d1c760bca397ed", "generation_seconds_batch": 14.40893407992553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4911319315433502, "target_z": 0.0019531206842717077, "ce": 5.605623245239258, "genuineness": 4.469690799713135, "identity": 0.7778408527374268, "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_Disappointment/0a57415a1d828b5172e78167d134e2aabf68fc4abfa2200d61834e54091c4a13.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "0a716191e6d79ec5b61156f2e7179ae01bfa299491348643a3dd81a885cb816f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "76b0031dff0e3c294241c86b4573a3ec37303590221f472cffab6f27e6350ca7", "generation_seconds_batch": 19.198190790018998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25004586577415466, "target_z": -0.3417968846273939, "ce": 5.831989288330078, "genuineness": 4.582659721374512, "identity": 0.7406265735626221, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0a716191e6d79ec5b61156f2e7179ae01bfa299491348643a3dd81a885cb816f.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": "0bd9a8eea7478636dbc90cb56d829dda8ee905012fdddefb31861d6e29bacf18", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6afda385f432ac045941ae788a8548b641f2a0fb131448020bc2584fa640c71c", "generation_seconds_batch": 19.510038323001936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0102888345718384, "target_z": 0.7421874747695885, "ce": 5.752562999725342, "genuineness": 4.532451152801514, "identity": 0.8054985404014587, "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_Disappointment/0bd9a8eea7478636dbc90cb56d829dda8ee905012fdddefb31861d6e29bacf18.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "0c08459b689c0de5a32e6fe7603b12ffe250db64665f8f000c12b9cc2aa54dd1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "07a15ba2c2d643f92e5f99787929456314211a37069c10446248990a2f4d7d42", "generation_seconds_batch": 19.03942416398786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27059298753738403, "target_z": -0.31249998937666884, "ce": 5.478540420532227, "genuineness": 4.68307638168335, "identity": 0.6664530038833618, "hypothesis": "La porte 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_Disappointment/0c08459b689c0de5a32e6fe7603b12ffe250db64665f8f000c12b9cc2aa54dd1.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "0c0fd200c302b174017c14ef2808e25d286595d1df597f7e5616deca471a6ae1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ef967fb8d9d360b257dbe559603ce92c0b33c85cad99089dd948a6518bfbb77d", "generation_seconds_batch": 21.558674758067355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18566492199897766, "target_z": -0.43359376925478776, "ce": 5.649308204650879, "genuineness": 4.482243061065674, "identity": 0.47856178879737854, "hypothesis": "The 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_Disappointment/0c0fd200c302b174017c14ef2808e25d286595d1df597f7e5616deca471a6ae1.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "0c18563308c967605ccbedc426861cd25d00a57a1f4c357bf5f8f4454e747b11", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8240877bb4078889fcc4725f999581ebcaf8e1feb15ee62d97c126e24718c819", "generation_seconds_batch": 14.415339317987673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12265381217002869, "target_z": -0.5234374907045852, "ce": 6.41180419921875, "genuineness": 4.971774101257324, "identity": 0.656436562538147, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0c18563308c967605ccbedc426861cd25d00a57a1f4c357bf5f8f4454e747b11.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": "0c187710dde24c13f156ba60ebbc1ed44c4bdd0060870f8388bc6668b6f7f89f", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0fdb1a631e295a40acc2a49887f66deb02c63cef5bf89fa7b39dc5c2446c9b76", "generation_seconds_batch": 19.181008634041063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29250991344451904, "target_z": -0.2812499734416721, "ce": 5.879645347595215, "genuineness": 4.645420074462891, "identity": 0.669654130935669, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0c187710dde24c13f156ba60ebbc1ed44c4bdd0060870f8388bc6668b6f7f89f.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "0c2d9d193ccc15805e36dd22326a5ba1048d2473c49e5c3d6644401e43c53133", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "283149d8fc6c4f4e0c00cdd0af4e15c11075a6e594f36978fc23450734f39eca", "generation_seconds_batch": 19.303866153932177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31442680954933167, "target_z": -0.25, "ce": 5.617537498474121, "genuineness": 4.582659721374512, "identity": 0.5618249177932739, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0c2d9d193ccc15805e36dd22326a5ba1048d2473c49e5c3d6644401e43c53133.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": "0c4626707445878b52018c60271f9f4073675efb9949b5f6802d2ce73ff21c1d", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7269a6b1e5ba84769a33ef890e4ed55cc49c93cf4a3528d2f7710c5bce781a61", "generation_seconds_batch": 15.125352235976607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2623741328716278, "target_z": -0.3242187559756238, "ce": 5.645336627960205, "genuineness": 4.632867813110352, "identity": 0.6450104117393494, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0c4626707445878b52018c60271f9f4073675efb9949b5f6802d2ce73ff21c1d.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": "0c68ebff6f203af3bb6b0c909394978899726999f40e779708e1bdce10c04fc2", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a234433fa2267b584d912fc3aba875a2326a47ec43196bcc9396e7deed6d2d00", "generation_seconds_batch": 14.41395164001733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33223432302474976, "target_z": -0.22460934611781835, "ce": 5.77639102935791, "genuineness": 4.758388519287109, "identity": 0.6976673603057861, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0c68ebff6f203af3bb6b0c909394978899726999f40e779708e1bdce10c04fc2.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "0c77ea65fcb893a048d1383ef36760ae63c6502311c6a716ca1df4cf2c8ecb1a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f053d2db1c242ca5dd5e5007558e9d38fc5cb99f981713db98b2c1d9ee4fa0a6", "generation_seconds_batch": 18.906430852017365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1801857054233551, "target_z": -0.4414062519918746, "ce": 5.839932441711426, "genuineness": 4.3504462242126465, "identity": 0.4044375717639923, "hypothesis": "The 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_Disappointment/0c77ea65fcb893a048d1383ef36760ae63c6502311c6a716ca1df4cf2c8ecb1a.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "0c83b3d180f45e77cb75f47bf0c32c2fb99305f8525b47fd0401bd06b2c06ef1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "696cdb5091239ee3155786449d93476fd4626b879bb691664eeaa19beed9276a", "generation_seconds_batch": 19.77196899894625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2048422396183014, "target_z": -0.4062499946883344, "ce": 6.109982967376709, "genuineness": 4.796044826507568, "identity": 0.6918562650680542, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0c83b3d180f45e77cb75f47bf0c32c2fb99305f8525b47fd0401bd06b2c06ef1.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": "0c97209d964050d7c455db120df8aaf344c1e2cd700db4e118c4619f493d8c84", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9893c1adb40d4d76ab58abe2e71a9a5e86fbb56247324759ab57f77b3ea58074", "generation_seconds_batch": 15.056082320981659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1870347559452057, "target_z": -0.43164060607719135, "ce": 5.601652145385742, "genuineness": 4.7081804275512695, "identity": 0.7879610061645508, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0c97209d964050d7c455db120df8aaf344c1e2cd700db4e118c4619f493d8c84.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": "0c97896bf30bfe225294bdfa833898e1c8528934c3a1f98df29d6f7983e3e3f4", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e839af392086064dcee725f392663b8c99c7041680902ee5bb37eeeeb187cd63", "generation_seconds_batch": 14.765076454961672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.269223153591156, "target_z": -0.31445315255426526, "ce": 5.585766792297363, "genuineness": 4.507347106933594, "identity": 0.6042776703834534, "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_Disappointment/0c97896bf30bfe225294bdfa833898e1c8528934c3a1f98df29d6f7983e3e3f4.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "ee08822f2b93cf5c25af42e53acb1da55c2002a4d9cced4a512b3403677922dd", "generation_seconds_batch": 16.317306171054952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15963861346244812, "target_z": -0.47070310474927496, "ce": 6.348263263702393, "genuineness": 4.394378662109375, "identity": 0.8025839328765869, "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_Disappointment/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "0d3efe1ec79a1eeb36b5aad4ae8f48d96ba2a8268da27f71372d01d8b77f912f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d6aaa65689c9f00a3233ccc008b678b1406c216d794b2fa16f3f2e3bfd7eb0f0", "generation_seconds_batch": 22.048881554976106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2760722041130066, "target_z": -0.304687506639582, "ce": 5.434855937957764, "genuineness": 4.68307638168335, "identity": 0.47073686122894287, "hypothesis": "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_Disappointment/0d3efe1ec79a1eeb36b5aad4ae8f48d96ba2a8268da27f71372d01d8b77f912f.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "0de6d18220ddd6d67e4ab2c776e67d07a8b1db95cd66e5d68316b4b3c741cf44", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0bb0e0c54a49f0afc570488b88fe269ded90a0bc4082eb9ede33d6ab4f1e4c9d", "generation_seconds_batch": 21.37852370494511, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07608035206794739, "target_z": -0.5898437639431222, "ce": 6.356205940246582, "genuineness": 4.6705241203308105, "identity": 0.161173477768898, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0de6d18220ddd6d67e4ab2c776e67d07a8b1db95cd66e5d68316b4b3c741cf44.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "0e1046a1bd00bc1d288e72b95dbaff539c47aa4d680a0f0b67c8d975a38c5d75", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6eb3069b17d0ca618f0f3507f2b29d5c1c06af994a1b6d1b7f8284aa871a3b73", "generation_seconds_batch": 19.275460788980126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.144529938697815, "target_z": 0.933593726761463, "ce": 5.839932441711426, "genuineness": 4.457139015197754, "identity": 0.4149593412876129, "hypothesis": "De deur 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_Disappointment/0e1046a1bd00bc1d288e72b95dbaff539c47aa4d680a0f0b67c8d975a38c5d75.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "0e68ca9d58cd374a1aa81852a78947bb4522004b00ac1fb1103671c4ba2274b4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5ac8ec70735b2a1ba42879efd76d33aa527989cfae0a1cc351ab818cb4649e37", "generation_seconds_batch": 16.020156911108643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15415936708450317, "target_z": -0.4785156299796865, "ce": 6.125868320465088, "genuineness": 4.256305694580078, "identity": 0.18152201175689697, "hypothesis": "The 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_Disappointment/0e68ca9d58cd374a1aa81852a78947bb4522004b00ac1fb1103671c4ba2274b4.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": "0f135002927a2f8e25bc1070253a22d55392b558940f20ad8f36017849216eca", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "ee4654a7e444f8e6c941edff06d099b72aba2e95ed8663f3aa226f12b150e380", "generation_seconds_batch": 15.424835161073133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2623741328716278, "target_z": -0.3242187559756238, "ce": 4.980137825012207, "genuineness": 4.306513786315918, "identity": 0.4749070405960083, "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": 0.120000000000001, "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_Disappointment/0f135002927a2f8e25bc1070253a22d55392b558940f20ad8f36017849216eca.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "0f887b605ff2effab35d23c51ab70394802cf8a8573592c9db55e95dcea4142b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8a7919c0487b1ef7632471f6367f889faefb7cbb6321a7a69e27cd7dd57b40ef", "generation_seconds_batch": 22.335487043950707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6363314986228943, "target_z": 0.2089843806436447, "ce": 6.205295085906982, "genuineness": 4.720732688903809, "identity": 0.33106645941734314, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/0f887b605ff2effab35d23c51ab70394802cf8a8573592c9db55e95dcea4142b.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "0fce5d4279e06c1009e923da1fd344b0a9561ef00f8be057c22b356d63ec9ef6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2d1dcb33107acf1be93bdf8e028774d9e9ea8943dff36a4d84a848f6ad23b8d8", "generation_seconds_batch": 21.30608138302341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1911441683769226, "target_z": -0.4257812440243762, "ce": 5.998785495758057, "genuineness": 4.7834930419921875, "identity": 0.8770545721054077, "hypothesis": "J'ai trouvé la 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_Disappointment/0fce5d4279e06c1009e923da1fd344b0a9561ef00f8be057c22b356d63ec9ef6.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": "0fcffacebe9ecf3ee3e5bcbd00bba2899ec02ba59474a62afcd96e8acece4601", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1870273b7067f56a4254c6293fe5800bbfeee6fb5de72f3cef45489a4f4d195a", "generation_seconds_batch": 14.378011813038029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5137337446212769, "target_z": 0.034179675714741974, "ce": 5.577824115753174, "genuineness": 4.444586753845215, "identity": 0.1824926882982254, "hypothesis": "De sleutels liggen op de keukentafel. Ik kijk in de la en daarna is 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_Disappointment/0fcffacebe9ecf3ee3e5bcbd00bba2899ec02ba59474a62afcd96e8acece4601.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "102e2bea2ad2882b507ffc244b69f11f8ddbacf2bff88033a0b3c6f423edfd61", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4105127cb8e0e5c0e77e9f3f1fe0dd7bfa28d5b8cf61ff2cf8fd3c04cdf39c45", "generation_seconds_batch": 19.419519890099764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33908334374427795, "target_z": -0.2148437426964598, "ce": 5.744620323181152, "genuineness": 4.6956281661987305, "identity": 0.6195844411849976, "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_Disappointment/102e2bea2ad2882b507ffc244b69f11f8ddbacf2bff88033a0b3c6f423edfd61.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "1066b3b6cdb9d9dd71e0898282e29ba9520a5bb86d2ef38a33b454e016ae691b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "026633ea6b6ce04b6cc6b043e777f325aad93da913b1419e5fad53a1f74e825c", "generation_seconds_batch": 18.919371469994076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09251806139945984, "target_z": -0.5664062307452122, "ce": 6.117925643920898, "genuineness": 4.444586753845215, "identity": 0.5169623494148254, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1066b3b6cdb9d9dd71e0898282e29ba9520a5bb86d2ef38a33b454e016ae691b.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "107afda6ea66a5b41370467bf92c86302a76d6c5bde4ed49204407ca5ffe39e0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "24580dc64c59d94a62c178ae4888343274f01620cb6ca33841fd8640a6fb20bf", "generation_seconds_batch": 21.36704981001094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11717456579208374, "target_z": -0.5312500159349968, "ce": 5.80021858215332, "genuineness": 4.7081804275512695, "identity": 0.47775328159332275, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/107afda6ea66a5b41370467bf92c86302a76d6c5bde4ed49204407ca5ffe39e0.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "10dcb97f4a659c8a03d179ef54c8ab1b8fcc0f602304765f758f38a5556b8a52", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ef4dd3d8db6df14740fdb5de6f4ce692e476142f107467fbe14747d7bfd756e4", "generation_seconds_batch": 15.64164120098576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41031330823898315, "target_z": -0.11328125464770739, "ce": 5.967014789581299, "genuineness": 4.6705241203308105, "identity": 0.7314772009849548, "hypothesis": "J'ai trouvé m 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_Disappointment/10dcb97f4a659c8a03d179ef54c8ab1b8fcc0f602304765f758f38a5556b8a52.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": "10e3adb65ab6f162f7cd8ae078ca1dc1c731ee8dce17c768bddd9608add4f46d", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c88ed976bfeba81447ced31d2be13eb9e104989ec7c565c3354d037c37eebb9e", "generation_seconds_batch": 14.504066177993082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2979891300201416, "target_z": -0.27343749070458523, "ce": 5.478540420532227, "genuineness": 4.356721878051758, "identity": 0.8038678169250488, "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_Disappointment/10e3adb65ab6f162f7cd8ae078ca1dc1c731ee8dce17c768bddd9608add4f46d.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "112656486216bc9075750a6b2d564f49fe563f75195f4ee4cb13ece84e78e119", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "60fadccb1819c4b19f9e87bd32c563caa87b903a5c757577b9f5920e6d69b77d", "generation_seconds_batch": 22.70765170804225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20347243547439575, "target_z": -0.4082031153726061, "ce": 6.284721851348877, "genuineness": 4.193545341491699, "identity": 0.45463645458221436, "hypothesis": "The 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_Disappointment/112656486216bc9075750a6b2d564f49fe563f75195f4ee4cb13ece84e78e119.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "1163515ff1e84d596937c17fbebb8568cd860fa66c0b5c17feb1713c9393da35", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c32f33c33729d55ca6e1b7a44550de562bbd3bd9de400275bf37469045d8d567", "generation_seconds_batch": 14.37995256204158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10621613264083862, "target_z": -0.5468749814091705, "ce": 6.332377910614014, "genuineness": 4.758388519287109, "identity": 0.5591423511505127, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1163515ff1e84d596937c17fbebb8568cd860fa66c0b5c17feb1713c9393da35.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "119f6ad9ec3c0fb102c5aae5bea062c30c706749340265d12d5b669b24f6e72b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f0163c4d99f71745d6eec7532b952b66389a96f385cb30cc8946725fe483ca67", "generation_seconds_batch": 19.033430582960136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16100841760635376, "target_z": -0.46874998406500323, "ce": 6.23706579208374, "genuineness": 4.796044826507568, "identity": 0.41253793239593506, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/119f6ad9ec3c0fb102c5aae5bea062c30c706749340265d12d5b669b24f6e72b.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": "11e65c3dfa1be5b106035da3fce4b42a225586128456a7dcab9f71fc3bd5b0b0", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4df1d6b163ad0c51639ca1b081736ca4c3909c575018ae56b3b96bf51eca6e20", "generation_seconds_batch": 14.510121461004019, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.355521023273468, "target_z": -0.1914062519918746, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.4448573887348175, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know and we can talk.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/11e65c3dfa1be5b106035da3fce4b42a225586128456a7dcab9f71fc3bd5b0b0.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "11fc1eecf6b53a85324cc636af768c568a129621a117a0e449693bd5748435e6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5de6b64b6abf9dc00adb36f3bd04747853a051ccc9e94e7dc58ddcdb31d289be", "generation_seconds_batch": 19.29861100600101, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1911441683769226, "target_z": -0.4257812440243762, "ce": 6.125868320465088, "genuineness": 4.331617832183838, "identity": 0.8159075975418091, "hypothesis": "La porte 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_Disappointment/11fc1eecf6b53a85324cc636af768c568a129621a117a0e449693bd5748435e6.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "127c30c7108ed4dd62d4d27b497efa547f92567272a643fdfb336bf928ff7f71", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ac85970ce11e56446b336306626bad1006a3dcae40cde493e825ad8b6f6f3072", "generation_seconds_batch": 19.155882952036336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2116912603378296, "target_z": -0.3964843912669759, "ce": 5.9431867599487305, "genuineness": 4.946669578552246, "identity": 0.6741031408309937, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/127c30c7108ed4dd62d4d27b497efa547f92567272a643fdfb336bf928ff7f71.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "52ad848304eb87506cefdc6b67634ef1b32f107150e6a68ccf9eeb388e7388e1", "generation_seconds_batch": 16.363518350059167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12813302874565125, "target_z": -0.5156250079674984, "ce": 6.205295085906982, "genuineness": 4.519899368286133, "identity": 0.6156451106071472, "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_Disappointment/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.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": "133aa94f79679707614f90512e0c7eaa3c9223967bf90c3257b853f24f399b4d", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85ccaa52c185c9111e3040cb597579d21fa56147d7746407fd83ca2fedb17f8e", "generation_seconds_batch": 14.504066177993082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22401952743530273, "target_z": -0.37890626261520577, "ce": 5.557967185974121, "genuineness": 4.846253395080566, "identity": 0.85161292552948, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et verifie les deux derniers chiffres. Appelle-moi quand tu auras a 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_Disappointment/133aa94f79679707614f90512e0c7eaa3c9223967bf90c3257b853f24f399b4d.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "13675cba84142c20ceb49c1fa51bc30d6b5ffd0ba50ef22e2b52e18228dc0f46", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d48dcc18f6153010f6db6999de4dd2bbd303f07e03d12ce9edf29cea072f99a6", "generation_seconds_batch": 19.988078312017024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16100841760635376, "target_z": -0.46874998406500323, "ce": 6.340320587158203, "genuineness": 4.231201171875, "identity": 0.33757516741752625, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/13675cba84142c20ceb49c1fa51bc30d6b5ffd0ba50ef22e2b52e18228dc0f46.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "14b585abac814b7482d9be7c4f96065ab8d4bcc20b68991bf727ff2eb32c2af5", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e7cde8ffbdcca09587b96549967aeb65c0fc962c19ce6c65df55239a7ca2b6ec", "generation_seconds_batch": 16.075285686994903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09525766968727112, "target_z": -0.5624999893766688, "ce": 6.23706579208374, "genuineness": 4.457139015197754, "identity": 0.220560222864151, "hypothesis": "The 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_Disappointment/14b585abac814b7482d9be7c4f96065ab8d4bcc20b68991bf727ff2eb32c2af5.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": "15286eb89cba94b6d53c886b106f5a14e34d15091348bd924abd1d8de1de981a", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "8f4ebd62f9dbdc85b3e2f2de07242419bba450eb3bee6608614754e26499c383", "generation_seconds_batch": 14.474110077950172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3870266079902649, "target_z": -0.14648434877365116, "ce": 5.863759994506836, "genuineness": 4.582659721374512, "identity": 0.5033851265907288, "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": 0.120000000000001, "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_Disappointment/15286eb89cba94b6d53c886b106f5a14e34d15091348bd924abd1d8de1de981a.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "153a1b55af0b4d21002efc1564d2e96be8220d340bba6d74b70fdaa8f8f0380e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6c0bb4acf2835b6ce9a27d401767d8df94f5378de232e26dbc5a68e5f99a61bc", "generation_seconds_batch": 19.24818728293758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.240457221865654, "target_z": -0.3554687506639582, "ce": 6.141753673553467, "genuineness": 4.959221839904785, "identity": 0.7582152485847473, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/153a1b55af0b4d21002efc1564d2e96be8220d340bba6d74b70fdaa8f8f0380e.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "1e45965a49e8de58c9d66458c86fe6e1839c6f98dc3b851a56a08082b7b5c1dc", "generation_seconds_batch": 16.008061555912718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12265381217002869, "target_z": -0.5234374907045852, "ce": 6.221180438995361, "genuineness": 4.306513786315918, "identity": 0.5437759160995483, "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_Disappointment/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "1567ce7f92d0d0c85f50cd4444954c1024c023e7689337c12db5abaf39717381", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6065a7fbe252db01564e3fcdaef71e1772f78c8c9e9780e8f734fdfcee5574f8", "generation_seconds_batch": 19.25128011102788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1938837766647339, "target_z": -0.4218750026558328, "ce": 5.863759994506836, "genuineness": 4.896461486816406, "identity": 0.6683626174926758, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1567ce7f92d0d0c85f50cd4444954c1024c023e7689337c12db5abaf39717381.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "15a10e745d6cc6f03077d1ae0d44d86dca39d8cca5f525a695c681d8cc5aa8e5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8f1f3fa9c76de739d96158d27f1cec5b7f2c30cfe637a09e1cc8b3ef59966316", "generation_seconds_batch": 21.60452004696708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3089475631713867, "target_z": -0.25781252523041154, "ce": 6.141753673553467, "genuineness": 4.281409740447998, "identity": 0.6998593807220459, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/15a10e745d6cc6f03077d1ae0d44d86dca39d8cca5f525a695c681d8cc5aa8e5.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "16a2f339aef1437fd3150fe1387425a17b431f1e342df32872ede5de2a21ada1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0368a127128d16632e0dba6763fd74d5c55f0515c2aef95c25bfd2014a96b024", "generation_seconds_batch": 19.767171832965687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08429920673370361, "target_z": -0.5781249973441672, "ce": 5.903473377227783, "genuineness": 4.720732688903809, "identity": 0.2768744230270386, "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_Disappointment/16a2f339aef1437fd3150fe1387425a17b431f1e342df32872ede5de2a21ada1.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "16a66d1893464d96e59101ccaa215c95ca2c75d750a9b54268c70f5eb098ee9d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6d5797c75ef3af66a5554394bb8515ce839a74170272a3d79122122d982f53b6", "generation_seconds_batch": 18.959899227018468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44592830538749695, "target_z": -0.06249998937666882, "ce": 5.577824115753174, "genuineness": 4.444586753845215, "identity": 0.267441987991333, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/16a66d1893464d96e59101ccaa215c95ca2c75d750a9b54268c70f5eb098ee9d.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "16ab74c16d2e196225931be500d306a67be32abba661525591d0ac9b69b1fc86", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "24818b090b6d357c70e42dc1fd65d9ab7def027ed73eb3a6b731f5a5dcaecbae", "generation_seconds_batch": 20.013488412019797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27881181240081787, "target_z": -0.30078126527103854, "ce": 6.117925643920898, "genuineness": 4.432034492492676, "identity": 0.4428851008415222, "hypothesis": "De deur staat nog open. Ik heb pias 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_Disappointment/16ab74c16d2e196225931be500d306a67be32abba661525591d0ac9b69b1fc86.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "1704954cb1f24e96e1d0c60f26731a6ef71eb95d39e12b050cbc281dc9988e8c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ad9132ead83115785861688c03a845c5e65d28d6561585a0cb79e8d15450e6a3", "generation_seconds_batch": 19.731989415944554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16785743832588196, "target_z": -0.45898438064364466, "ce": 6.173524379730225, "genuineness": 4.796044826507568, "identity": 0.6912585496902466, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1704954cb1f24e96e1d0c60f26731a6ef71eb95d39e12b050cbc281dc9988e8c.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "170e8a64411cfe383e175a8c7981ab0ea5f0359ee127cdc53d21b3b8ce543275", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "55db846de801038ba847c4c6e7e068ab4e5b5de619562c776f96f328d263a7f6", "generation_seconds_batch": 19.306154298014008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3363437056541443, "target_z": -0.21875002655832795, "ce": 5.585766792297363, "genuineness": 4.6956281661987305, "identity": 0.5823178291320801, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/170e8a64411cfe383e175a8c7981ab0ea5f0359ee127cdc53d21b3b8ce543275.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "173c58e5c433ea0d4e4389936bcc209f1a03bcef0d048775671b3b91ebf6a864", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c97d0692331b29126ead0329805f4ce057dcc81234a05ae3f98ee995f348e05", "generation_seconds_batch": 19.424026191001758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 5.546053409576416, "genuineness": 4.042920112609863, "identity": 0.44485926628112793, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/173c58e5c433ea0d4e4389936bcc209f1a03bcef0d048775671b3b91ebf6a864.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "181163d464abe1ff3a4a857052b0230ccfda9127147124ba60d692f08b61ec5d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f3263fc6514031109e37e09ef0190cfd74ec424a5f4b77021d0f839f5be3dc41", "generation_seconds_batch": 22.193127745995298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07334074378013611, "target_z": -0.5937500053116656, "ce": 5.6532793045043945, "genuineness": 4.557555198669434, "identity": 0.44741880893707275, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/181163d464abe1ff3a4a857052b0230ccfda9127147124ba60d692f08b61ec5d.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "18242686e0240a0aeeaa939fd5696f67cab86dcc0ebca9a6ae05137b8e3539f1", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f88ad12fc0fa5820b639cfda4b9be7bbc36a1517653eadc680a500ac213afa7b", "generation_seconds_batch": 17.668881096993573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22538933157920837, "target_z": -0.37695314193093404, "ce": 6.23706579208374, "genuineness": 4.582659721374512, "identity": 0.6894983649253845, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/18242686e0240a0aeeaa939fd5696f67cab86dcc0ebca9a6ae05137b8e3539f1.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "182d201cba7a19bab8022ab330ab54615aa6706f9b3539f1eb8f1317358a761f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d2241a1700c9a6389ce6d7977f96952b16d92d170b66dc119e91d3eca28d72a0", "generation_seconds_batch": 14.49425812496338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.484282910823822, "target_z": -0.007812482737086831, "ce": 6.0305562019348145, "genuineness": 4.6705241203308105, "identity": 0.6040993928909302, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/182d201cba7a19bab8022ab330ab54615aa6706f9b3539f1eb8f1317358a761f.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": "184953218bf8208d20c98b738b3de3170da393b4b7e678748a800353fcd396d1", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61e3bdec9364b58b78cc5de514c471bbaabea6753f46c194c4853c86ca45898e", "generation_seconds_batch": 14.698859486030415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19662338495254517, "target_z": -0.4179687612872894, "ce": 5.617537498474121, "genuineness": 4.632867813110352, "identity": 0.605451762676239, "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_Disappointment/184953218bf8208d20c98b738b3de3170da393b4b7e678748a800353fcd396d1.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": "1859580fd631204c54602ce0d2bbf4042142b4dfe37fd76fb558e5293405f3bc", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2563fdd44086d29b2acb4166caf12504f7dc537e03ab6aa417a7776562cfb6a7", "generation_seconds_batch": 14.871957016992383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23223838210105896, "target_z": -0.3671874960162508, "ce": 5.8875885009765625, "genuineness": 4.369274139404297, "identity": 0.5984073877334595, "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_Disappointment/1859580fd631204c54602ce0d2bbf4042142b4dfe37fd76fb558e5293405f3bc.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": "1859df8ce95ef771118b1d86373df018ae8a22de9fbb537efe6d429ae33bc170", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "27b78314c61cb1cab5a1783d1cc803ad7c1396d3c82c8c94f500e315d88c8e9d", "generation_seconds_batch": 19.503900429001078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21991011500358582, "target_z": -0.3847656246680209, "ce": 5.998785495758057, "genuineness": 4.168440818786621, "identity": 0.38260897994041443, "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_Disappointment/1859df8ce95ef771118b1d86373df018ae8a22de9fbb537efe6d429ae33bc170.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "18c17c830fd9e34621bf6c01cc98834621101dbdd75260907a26447598544c36", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "03fbd612114d2a644e1158032b9073aa7d587c26139856eaec5db0fa9fee995a", "generation_seconds_batch": 16.600425380980596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2870306670665741, "target_z": -0.2890624986720836, "ce": 5.816103935241699, "genuineness": 4.65797233581543, "identity": 0.6758642196655273, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/18c17c830fd9e34621bf6c01cc98834621101dbdd75260907a26447598544c36.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "18de84d5bb479d5c7a6b6316ad3cd61a312bb302c0df589004406c48bf72d701", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "36451f371cb9e5b63cb6b5d37a88ad41c3f197ad807e788a411801498de49ce1", "generation_seconds_batch": 21.36704981001094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1582687795162201, "target_z": -0.4726562679268714, "ce": 5.903473377227783, "genuineness": 4.7081804275512695, "identity": 0.6389288902282715, "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_Disappointment/18de84d5bb479d5c7a6b6316ad3cd61a312bb302c0df589004406c48bf72d701.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "18f259439c3fb25c54c2989365e8a78da00d5ef3cb77542d2b5a5100b28c209a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4e7cc7c4d5c31fb40d1980c7920d50f3bd5dd88e7aafc8f5842aa5c1fbe996e0", "generation_seconds_batch": 20.11246056202799, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1336122751235962, "target_z": -0.5078124827370868, "ce": 6.1894097328186035, "genuineness": 4.557555198669434, "identity": 0.696368932723999, "hypothesis": "La porte 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_Disappointment/18f259439c3fb25c54c2989365e8a78da00d5ef3cb77542d2b5a5100b28c209a.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": "19d9f4b0ea476008b6bd2f3a4b50a9720f8a7606cf2033896e06cb5d2843565d", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e423bd2fa3dcd8d6c34fbb6c09cebe95f26f4eaa25f1901092864571d05d2175", "generation_seconds_batch": 14.564329573069699, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4650647640228271, "target_z": 1.3906249017341865, "ce": 5.982900142669678, "genuineness": 4.909013748168945, "identity": 0.6958324313163757, "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_Disappointment/19d9f4b0ea476008b6bd2f3a4b50a9720f8a7606cf2033896e06cb5d2843565d.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "1a2ac1635e8ad366a7922873e2d78c56300559707f00f8b6c92eaf8615f9b064", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d5406789d42610458fc4a199cefe7c702aa24b1979ac1ba89229a003f723c5fd", "generation_seconds_batch": 19.767171832965687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15963861346244812, "target_z": -0.47070310474927496, "ce": 5.577824115753174, "genuineness": 4.6705241203308105, "identity": 0.4621470868587494, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1a2ac1635e8ad366a7922873e2d78c56300559707f00f8b6c92eaf8615f9b064.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "1a573595f82c527adcfdbe09cfa6dcc0cc32d4e715316276ef09282cbae508c3", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0f07082b42a34f9f8dec227e642f9919a682a57800d8c9bbc0f15ec299835779", "generation_seconds_batch": 21.558674758067355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13087263703346252, "target_z": -0.511718766598955, "ce": 5.685050010681152, "genuineness": 4.3881025314331055, "identity": 0.3045705258846283, "hypothesis": "The 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_Disappointment/1a573595f82c527adcfdbe09cfa6dcc0cc32d4e715316276ef09282cbae508c3.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "1abf9f710ffa5076ce1c98dd4a7911c7c43aca05f0ba7b66940e3c87740eeaeb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d589f075752c252d9420dda962bd8a9940d8fdd729d65f270373a5bd402d7ec3", "generation_seconds_batch": 19.134846278000623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8267346620559692, "target_z": 0.4804687081706335, "ce": 5.760505676269531, "genuineness": 4.344170093536377, "identity": 0.23000770807266235, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1abf9f710ffa5076ce1c98dd4a7911c7c43aca05f0ba7b66940e3c87740eeaeb.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "1ac0306148cb21b03b3050e35c30a62fc641b3aea60d989ad92797b492a7d12d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7309d3bb7c011b8444feab06eed8ac1e15fb6b2ad630fbcc9376c34c6cb4d05a", "generation_seconds_batch": 19.18494679708965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33223432302474976, "target_z": -0.22460934611781835, "ce": 5.855817794799805, "genuineness": 4.7458367347717285, "identity": 0.7237316370010376, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1ac0306148cb21b03b3050e35c30a62fc641b3aea60d989ad92797b492a7d12d.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "1ad7e73935bfffda9340db38f89f9d594281dcf3749d78b5bb8340ec0a50d02c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "20f6300e3a48e6faa57ea2e25ecefd0181ce3db90eae7d4945f3e00211cff825", "generation_seconds_batch": 20.986890834057704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25689488649368286, "target_z": -0.33203128120603537, "ce": 6.109982967376709, "genuineness": 4.595211505889893, "identity": 0.6847761869430542, "hypothesis": "La porte est encore ouverte. J'ai j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1ad7e73935bfffda9340db38f89f9d594281dcf3749d78b5bb8340ec0a50d02c.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": "1b6c6b074b4fa078aaec0ff4ec5eabf998e63d655668f66ad2c778a12de6db18", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a2fb2d8157902c3b8c03e870f289337844cda9df556a1e8aa78660865dac7f94", "generation_seconds_batch": 15.449887205963023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19936299324035645, "target_z": -0.414062519918746, "ce": 5.434855937957764, "genuineness": 4.118232727050781, "identity": 0.39919960498809814, "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_Disappointment/1b6c6b074b4fa078aaec0ff4ec5eabf998e63d655668f66ad2c778a12de6db18.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "1bbdd4b3351a48abc4884feba989f2d9fe70d14732f7925ef2e0629c5ce0b15e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a42a680cef3f10648d217338f4151e047d61c73f5c08c855135f272c1a1fe941", "generation_seconds_batch": 20.013488412019797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21443089842796326, "target_z": -0.39257810740510773, "ce": 5.982900142669678, "genuineness": 4.457139015197754, "identity": 0.5970223546028137, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1bbdd4b3351a48abc4884feba989f2d9fe70d14732f7925ef2e0629c5ce0b15e.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "1c0c5bb5172cbe8f26ca1f7ffa44f9d019e087e1ea53d68756de4d7ae516cf5d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ee4d0d992a3de5cf8279ef1e50214c5146bf8d97217ef5f8f3dcad09ea428e24", "generation_seconds_batch": 22.125738620990887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7349575757980347, "target_z": 0.349609324871156, "ce": 6.0305562019348145, "genuineness": 4.532451152801514, "identity": 0.48695528507232666, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1c0c5bb5172cbe8f26ca1f7ffa44f9d019e087e1ea53d68756de4d7ae516cf5d.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "1cf9261d2b62e1ae8c56f503603779556def0741425b47bd889090752c395750", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e701845184314b688281c5ed01e7023b93e1c340337d3c98f0fa70da2fac2d80", "generation_seconds_batch": 19.167338444967754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.676055908203125, "target_z": 0.2656250079674984, "ce": 5.9431867599487305, "genuineness": 4.871357440948486, "identity": 0.7700335383415222, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1cf9261d2b62e1ae8c56f503603779556def0741425b47bd889090752c395750.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "ae26b08108ec3dff833273d8465a22346559160519eb368ec6229741bce661eb", "generation_seconds_batch": 15.735080166952685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1623782217502594, "target_z": -0.4667968633807315, "ce": 6.141753673553467, "genuineness": 4.337893962860107, "identity": 0.8155754208564758, "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_Disappointment/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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "ea39fd0510ea5414d3f4ebf28b836b9ee694f0010644c3d0dd8e93fe299c2aae", "generation_seconds_batch": 15.907562467968091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22127991914749146, "target_z": -0.3828125039837492, "ce": 6.284721851348877, "genuineness": 4.494794845581055, "identity": 0.7293702363967896, "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_Disappointment/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "1e0e7c29b338f299235f09b66f9f38c4ba9e7fe0846cf96d15f2b89b54e24372", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4797b84f5963e3ef2156a2c27be4990c38dd671e1432608dd558a3f3e217dea3", "generation_seconds_batch": 14.191523195011541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2938796877861023, "target_z": -0.27929689525072504, "ce": 5.863759994506836, "genuineness": 4.7458367347717285, "identity": 0.7967441082000732, "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_Disappointment/1e0e7c29b338f299235f09b66f9f38c4ba9e7fe0846cf96d15f2b89b54e24372.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "1e1e8d53f0963068e500e2908f664027d9f440d42a3c232fad842af692dfc844", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "250ef5c7fdd787333670c3dac276f4c5df7f7412346c4b439d6ec47001b13df0", "generation_seconds_batch": 19.181637019035406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1514197587966919, "target_z": -0.4824218713482299, "ce": 5.538110733032227, "genuineness": 4.7834930419921875, "identity": 0.5058671832084656, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1e1e8d53f0963068e500e2908f664027d9f440d42a3c232fad842af692dfc844.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "1e6b1bde6f10247e5d1c890fea803cceaf2a51add70f4b305c0e34a9c3305d95", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "383cd11f6ad10a10d599d617737ecb59d1fa2e8563d966a948146f21d03dd4ca", "generation_seconds_batch": 15.83956362400204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32401543855667114, "target_z": -0.23632815521009803, "ce": 5.557967185974121, "genuineness": 4.7834930419921875, "identity": 0.5838506817817688, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1e6b1bde6f10247e5d1c890fea803cceaf2a51add70f4b305c0e34a9c3305d95.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "1e6d36f85529adda7abbc6b5b353ffd10f6f01e0d7c7448061375ca3d64d9bdc", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2a14973d5d9177eb2d70e64b661d44bbb93fc8b1cb76b9b9fec614ed723062af", "generation_seconds_batch": 19.16944828699343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5979769229888916, "target_z": 0.15429691649738742, "ce": 5.542081832885742, "genuineness": 4.6705241203308105, "identity": 0.6886851787567139, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1e6d36f85529adda7abbc6b5b353ffd10f6f01e0d7c7448061375ca3d64d9bdc.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "d801f44ad3491c6fa5a9b85d920c955596a67f9a23da84d5d54a7255d7022981", "generation_seconds_batch": 15.735080166952685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15278956294059753, "target_z": -0.4804687506639582, "ce": 6.125868320465088, "genuineness": 4.344170093536377, "identity": 0.5910305380821228, "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_Disappointment/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.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": "1f634cf4d17f57321380922381b8969c573d1c6c9b1873535e29e4984e8d40db", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fbafa50858bdde6ab5471017b94034ed7e9c1ce639343c71c9f6140343b9383b", "generation_seconds_batch": 14.3944423670182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1336122751235962, "target_z": -0.5078124827370868, "ce": 5.895530700683594, "genuineness": 4.570107460021973, "identity": 0.5760012269020081, "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_Disappointment/1f634cf4d17f57321380922381b8969c573d1c6c9b1873535e29e4984e8d40db.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "1f7c98e734dbbc153cde58b4f054aa8ba1c147a03546289d19f3f699c914c932", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "da45ee1ab194b4e850c702541cb5f02087eb8ab5af46b704f47ac97a00bae010", "generation_seconds_batch": 19.442150990013033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36784929037094116, "target_z": -0.1738281233401045, "ce": 5.673136234283447, "genuineness": 4.796044826507568, "identity": 0.6656278371810913, "hypothesis": "La porte 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_Disappointment/1f7c98e734dbbc153cde58b4f054aa8ba1c147a03546289d19f3f699c914c932.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "1fa094602e734006ad6c33d887acbd30c123e1b5bdabfde06129d27a2ad47820", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14fdb342fd7eddb08806a1d7c44097340a675d6cea31649d43dafd46c59e331d", "generation_seconds_batch": 14.197147555998527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47743386030197144, "target_z": -0.017578128651770095, "ce": 5.77639102935791, "genuineness": 4.796044826507568, "identity": 0.5697941780090332, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1fa094602e734006ad6c33d887acbd30c123e1b5bdabfde06129d27a2ad47820.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "1fb0f9d8773e4706623555db710c9937e6ac91041592f201920225f812ce363f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e6c60c826a2fb65694a1579bedd542b0489b1e8508fed0bc818537f0f2c8e95f", "generation_seconds_batch": 19.267409572028555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32127583026885986, "target_z": -0.24023439657864146, "ce": 5.816103935241699, "genuineness": 4.645420074462891, "identity": 0.49529898166656494, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/1fb0f9d8773e4706623555db710c9937e6ac91041592f201920225f812ce363f.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "1fb4c16c2210be47b029310adbb432a646edc5b7c129d9f1e0b4fbb2faec63d4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ab896ca76cc3739a99b125f1c461271a33b1c14f69ef16257f3716c5a9e4b5c8", "generation_seconds_batch": 19.28105674800463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15963861346244812, "target_z": -0.47070310474927496, "ce": 5.696964263916016, "genuineness": 4.6705241203308105, "identity": 0.7216570973396301, "hypothesis": "J'ai trouvé la 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_Disappointment/1fb4c16c2210be47b029310adbb432a646edc5b7c129d9f1e0b4fbb2faec63d4.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "1fcd892ce57f987ff7f8c57e695ee5ecab684458c7adddc478b60f6a6a1f86ea", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "49c1e8c6afa472b8509b0fbbf19f93aecc9bea2f3992d9b12b7fa3b3a76053d3", "generation_seconds_batch": 22.32634184602648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2979891300201416, "target_z": -0.27343749070458523, "ce": 5.959072113037109, "genuineness": 4.7081804275512695, "identity": 0.7878659963607788, "hypothesis": "J'ai trouvé la 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_Disappointment/1fcd892ce57f987ff7f8c57e695ee5ecab684458c7adddc478b60f6a6a1f86ea.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "2036af8c1f46daa8bc2221f0b470f0c4d44d04301c5f3eb3b0fdb91b88ff97f9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0a247c777127a5bf969363431fa636bd0ca91abc6d7b0cb4a4f11758d4a51db2", "generation_seconds_batch": 19.116253744112328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7294783592224121, "target_z": 0.34179684213406913, "ce": 5.982900142669678, "genuineness": 4.406930446624756, "identity": 0.4801509380340576, "hypothesis": "Ik 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_Disappointment/2036af8c1f46daa8bc2221f0b470f0c4d44d04301c5f3eb3b0fdb91b88ff97f9.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "203f3d265e8fcea33d71fa66e3db227c846ede318ed69936731dcb7afb2aa0c6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d719fb5a60c01def2ecdc985e8b741de85ee3c825c1648e9cd477bb500dd6ec3", "generation_seconds_batch": 20.228206739062443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11991420388221741, "target_z": -0.5273437320731287, "ce": 6.24500846862793, "genuineness": 4.344170093536377, "identity": 0.39509299397468567, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/203f3d265e8fcea33d71fa66e3db227c846ede318ed69936731dcb7afb2aa0c6.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "20582de36a906a080bf4124bc9d346c60c74e1f52f424889bd75d282bff6d7b0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "53758ca8f9058ed53df4d9a8e6c34ac5f1ef9ad9f667552a6efad08ad822b0c1", "generation_seconds_batch": 22.50045674503781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02128806710243225, "target_z": -0.6679687612872893, "ce": 6.38003396987915, "genuineness": 4.570107460021973, "identity": 0.38378390669822693, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/20582de36a906a080bf4124bc9d346c60c74e1f52f424889bd75d282bff6d7b0.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "2078d24068aef4c48cc37b1178bdd3a8f86eb5b8550648da2ecab5969b64703e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3a01258d191eb11dce3a7bd04451dc41205501cf174e46fa9f9e3ff69e2636da", "generation_seconds_batch": 19.369267383939587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2048422396183014, "target_z": -0.4062499946883344, "ce": 5.295859336853027, "genuineness": 4.6203155517578125, "identity": 0.5743526220321655, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2078d24068aef4c48cc37b1178bdd3a8f86eb5b8550648da2ecab5969b64703e.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": "20f6733baa79d81d5943f985d6598728f2061e1b316dec55474ee2cb0329dbf9", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f53d1c0beeaf717251f3e8b8b4020c09af467cdb9df345323c3c8a4ad6dbc262", "generation_seconds_batch": 14.58777686196845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1623782217502594, "target_z": -0.4667968633807315, "ce": 5.7128496170043945, "genuineness": 4.532451152801514, "identity": 0.3250651955604553, "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_Disappointment/20f6733baa79d81d5943f985d6598728f2061e1b316dec55474ee2cb0329dbf9.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "218c58eaa13016e5e53d6a9f7dd1afed68c8d4a7edd9959d0e270cea0ab7cbb0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ac7183677ef4e910591387c8d0f47b434724b4d5db91159f05ce22d4a6c9c2b3", "generation_seconds_batch": 19.349877258995548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20621204376220703, "target_z": -0.4042968740040627, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.5811381936073303, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/218c58eaa13016e5e53d6a9f7dd1afed68c8d4a7edd9959d0e270cea0ab7cbb0.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "21bbf1114731902c4157bd5923e92f7fc5fd9d1eaeb83272aab3602e3ec14632", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8fb282cf591916b41491aff31976521944f5d146ec2691fdd138df7b7f993735", "generation_seconds_batch": 16.69278168200981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13909149169921875, "target_z": -0.5, "ce": 5.649308204650879, "genuineness": 4.011539936065674, "identity": 0.548965573310852, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/21bbf1114731902c4157bd5923e92f7fc5fd9d1eaeb83272aab3602e3ec14632.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "21d82d46ab350f034c32e46edc72a0019f698bbcda70ec3db2f04bc347beebd0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a564a8e673525d9899ae8b31b5916544d5662082b99a09190532700b7de259c0", "generation_seconds_batch": 19.836100550019182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0048503875732421875, "target_z": -0.6914062519918746, "ce": 6.427689552307129, "genuineness": 4.507347106933594, "identity": 0.5644373297691345, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/21d82d46ab350f034c32e46edc72a0019f698bbcda70ec3db2f04bc347beebd0.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "2230d680be4316799585132277419a9faa1e73e8ec63e2e14820bf7f3f004776", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "86384f028d5aa7969dca5a447cecaac9d9e8067a1cf869213e51b640dc358110", "generation_seconds_batch": 19.606533956946805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.611674964427948, "target_z": 0.1738281233401045, "ce": 6.23706579208374, "genuineness": 4.896461486816406, "identity": 0.7382070422172546, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2230d680be4316799585132277419a9faa1e73e8ec63e2e14820bf7f3f004776.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "2230fb5c4ddc690ec3bd70f494942ed8f7bf07aef26ff08d45bbcf5fbeaec2a5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6ef15f53c38e5f699285d67cd0843c25dffdb20386f0ca98d88f08865e627d2c", "generation_seconds_batch": 20.833634293987416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6452352404594421, "target_z": 0.22167968633807314, "ce": 5.454712867736816, "genuineness": 4.344170093536377, "identity": 0.23210573196411133, "hypothesis": "De deur 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_Disappointment/2230fb5c4ddc690ec3bd70f494942ed8f7bf07aef26ff08d45bbcf5fbeaec2a5.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "22553d42a344cd3c4f8921fa8154b0bd002df6e74d098b427277253667ea7aba", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f31757a11d3dd82cc2f97e4bcc55db46f292c3e2f11a95389c9e9b78381a959c", "generation_seconds_batch": 19.275075062992983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45277732610702515, "target_z": -0.05273438595531028, "ce": 6.157639026641846, "genuineness": 4.507347106933594, "identity": 0.40668004751205444, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/22553d42a344cd3c4f8921fa8154b0bd002df6e74d098b427277253667ea7aba.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "2256074365ecb7df338c39e839d23bcedf2e00d6f37b96244f3af9dbaf1368db", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8eb80a2acc3cabfc7ad796d5bfdaa533eab09561bec422e831621eba55554178", "generation_seconds_batch": 19.99937877501361, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16100841760635376, "target_z": -0.46874998406500323, "ce": 6.24500846862793, "genuineness": 4.344170093536377, "identity": 0.40336769819259644, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2256074365ecb7df338c39e839d23bcedf2e00d6f37b96244f3af9dbaf1368db.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "228e13b8194419da347111b7451846b6e2c22daa9f35b815ecdaded0a8335cdb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "38abd8e3644b1ad61f10932b3aeaf6db0a434fff99a880b207c8c35b1edabf70", "generation_seconds_batch": 19.347304549999535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20621204376220703, "target_z": -0.4042968740040627, "ce": 5.816103935241699, "genuineness": 4.8588056564331055, "identity": 0.5463286638259888, "hypothesis": "he encontrado la cajita. estaba junto a la ventana vieja. podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/228e13b8194419da347111b7451846b6e2c22daa9f35b815ecdaded0a8335cdb.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "22becdc161eb09e937d25973ee718704440c92cd032e13186b5dcb069662a8b8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f3e9cf974a2c387c65f8b87bbe78b7ad4661abb05dce07da356fe19a4e0ac5d6", "generation_seconds_batch": 14.322613025084138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1719260215759277, "target_z": 0.9726561404468972, "ce": 5.839932441711426, "genuineness": 4.143336772918701, "identity": 0.4207604229450226, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/22becdc161eb09e937d25973ee718704440c92cd032e13186b5dcb069662a8b8.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "22f958df56bf7e7539c9aab99205974e12385225747f7eae5d45ae7cb2c1940e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fcb8e9b1dc1ed54ad3d3f0f767bae3021d09cce30e8c9a1579e6a492f3b5c13f", "generation_seconds_batch": 19.018552226014435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9198815822601318, "target_z": 0.6132812546477074, "ce": 5.967014789581299, "genuineness": 4.557555198669434, "identity": 0.626057505607605, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/22f958df56bf7e7539c9aab99205974e12385225747f7eae5d45ae7cb2c1940e.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": "233cd9c50d681573517a2e656dfb11dd74e908e20cf4d2ff6b3d3f56f0a1444b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15b380809a885492143c2318cfd77c53ee96bd8093a670a75526024e59af005f", "generation_seconds_batch": 14.60922791203484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43223023414611816, "target_z": -0.08203123871271062, "ce": 5.561938762664795, "genuineness": 4.582659721374512, "identity": 0.4349793493747711, "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_Disappointment/233cd9c50d681573517a2e656dfb11dd74e908e20cf4d2ff6b3d3f56f0a1444b.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "23c3f762cefba4b398d54c86f340bb5e244519fceb3c2ab37c1a9566d4c6bb8c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "24a3bcdff477ae16fbbc75e0002fe8d4565b3b1bebb02ea5efed2a2b7a0c69c5", "generation_seconds_batch": 19.03566255606711, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24867606163024902, "target_z": -0.3437500053116656, "ce": 5.617537498474121, "genuineness": 4.6203155517578125, "identity": 0.7554411888122559, "hypothesis": "J'ai trouvé la 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_Disappointment/23c3f762cefba4b398d54c86f340bb5e244519fceb3c2ab37c1a9566d4c6bb8c.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "24125453d83d5a5fd218bf999bad31db54aa3d18a7cac2e3a196b96a5c24a3e9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8abcb3a73294603b7cef729dabd81fa28bb95622eb1208ab288fe189a80ea023", "generation_seconds_batch": 19.033430582960136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07881999015808105, "target_z": -0.585937480081254, "ce": 5.919358730316162, "genuineness": 4.632867813110352, "identity": 0.5651618838310242, "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_Disappointment/24125453d83d5a5fd218bf999bad31db54aa3d18a7cac2e3a196b96a5c24a3e9.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "24225388758a5f4da0a7331664e1d5fc76d6e355ea4cd512e62cb1e902a9f835", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f9bc570e1b581d429cd3a0cec77987ec90b8e54dffb11053b12196d3648cc915", "generation_seconds_batch": 19.198190790018998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41305291652679443, "target_z": -0.10937501327916398, "ce": 5.935244083404541, "genuineness": 4.557555198669434, "identity": 0.872144341468811, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/24225388758a5f4da0a7331664e1d5fc76d6e355ea4cd512e62cb1e902a9f835.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "244ce50a28a6754724920415889257654715b8146f026e066d7cde8d50ea8734", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2921e08117bf684f4d89c2d527659db8ccb7ea2632b5d0b2d0e348855c0e7517", "generation_seconds_batch": 14.319756273995154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7637235522270203, "target_z": 0.390624986720836, "ce": 5.617537498474121, "genuineness": 4.8588056564331055, "identity": 0.4865797758102417, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/244ce50a28a6754724920415889257654715b8146f026e066d7cde8d50ea8734.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "24d52fc2b9a161d81f5b7b6155622fa674f59f001f00dc047c8223b6443a9845", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2cb6a7280ac034281b4739f49ab094bef12512a50ffabd091069b62ff361e16a", "generation_seconds_batch": 14.547612101072446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17470648884773254, "target_z": -0.44921873472896146, "ce": 6.125868320465088, "genuineness": 4.821148872375488, "identity": 0.6518155336380005, "hypothesis": "J'ai trouvé la 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_Disappointment/24d52fc2b9a161d81f5b7b6155622fa674f59f001f00dc047c8223b6443a9845.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "24f56cfb48e741c680989464a841307b6ff1b9d0c5e9b5afb5ad9a13c6734f0e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2fa2dcb93932d7b352681fdc5ef4fead1bb8d1806cd33905fd7e15f81ee30cbf", "generation_seconds_batch": 19.21523822005838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4445585012435913, "target_z": -0.06445311006094052, "ce": 5.311744689941406, "genuineness": 4.469690799713135, "identity": 0.7864009141921997, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/24f56cfb48e741c680989464a841307b6ff1b9d0c5e9b5afb5ad9a13c6734f0e.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "24faf0a19a35d3ede97943d23b1124029c431f948744a2fe8eda2f6a674b491c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b22cab6dc40bfc031e7fc44468cbd0d4488fce25c8122ca802ed29bf8f230fcb", "generation_seconds_batch": 20.641013584914617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8102970123291016, "target_z": 0.457031259959373, "ce": 5.863759994506836, "genuineness": 4.545003414154053, "identity": 0.5246517658233643, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/24faf0a19a35d3ede97943d23b1124029c431f948744a2fe8eda2f6a674b491c.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": "2626460709b3a1663652851a6fb139a52c25e53267c62538b50688e86267d361", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a710133b57aaab1e1cd9a76fdd29bd620927e6ee08dcbf0474d1fcd1d62b4b84", "generation_seconds_batch": 14.472954318975098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2021026313304901, "target_z": -0.41015623605687784, "ce": 6.0146708488464355, "genuineness": 4.645420074462891, "identity": 0.7599196434020996, "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_Disappointment/2626460709b3a1663652851a6fb139a52c25e53267c62538b50688e86267d361.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "263fc5984f399daac3321f53347bb4cf66f01d06ac8d9eee3504e911ff608437", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a933801bc1e7e7817e4729c2bbf8dbe408eeddee0141ee0276413ef3238f88ec", "generation_seconds_batch": 16.912312091095373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27881181240081787, "target_z": -0.30078126527103854, "ce": 5.760505676269531, "genuineness": 4.883909225463867, "identity": 0.7048530578613281, "hypothesis": "La porte 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_Disappointment/263fc5984f399daac3321f53347bb4cf66f01d06ac8d9eee3504e911ff608437.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "26becfdad9afb9fd7344ec724b819c8832cc6029021d4a7efd545d63e6aff6cb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2f9e50fd17beb863a6e8abbb8f223f3694455ed61f833cd3236de3fcdb672eca", "generation_seconds_batch": 22.191821706015617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07334074378013611, "target_z": -0.5937500053116656, "ce": 6.41180419921875, "genuineness": 4.7332844734191895, "identity": 0.2746717631816864, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/26becfdad9afb9fd7344ec724b819c8832cc6029021d4a7efd545d63e6aff6cb.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "76134180472da7d4a1140dd5962069e9942c6a02e26c78babf1d2f1c1d4038b2", "generation_seconds_batch": 14.482601386960596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15278956294059753, "target_z": -0.4804687506639582, "ce": 6.395919322967529, "genuineness": 4.419482707977295, "identity": 0.3567379415035248, "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_Disappointment/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "26ebdf053adcba7583a1df582b8daff5f2c0a7457090c0dadf24874a19a7c2be", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "577b91ee6d1044e954449ff48fcf7d6aa0a10abfdef283ae114b3de7db86fbac", "generation_seconds_batch": 16.607004103949293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5575675964355469, "target_z": 0.09667970758473551, "ce": 5.6334228515625, "genuineness": 4.645420074462891, "identity": 0.598397970199585, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/26ebdf053adcba7583a1df582b8daff5f2c0a7457090c0dadf24874a19a7c2be.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "27a223f8b9df8abfe0087f823f9b238fd98f18925ea0471700d418672f4d7033", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "00242483f3f899535ac2de5df69e4a0e17f2c3a72cd08eb97ef1818fe9e5cd19", "generation_seconds_batch": 19.75656656001229, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2719627916812897, "target_z": -0.3105468686923971, "ce": 6.0146708488464355, "genuineness": 4.356721878051758, "identity": 0.7809295654296875, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/27a223f8b9df8abfe0087f823f9b238fd98f18925ea0471700d418672f4d7033.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "27fe535509ad649374f784f5dceecc14c181d03097cabd4e9e9579e526486df5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "82df3a63c63693c2a464553d835fd9b950ba530e8c7e492020f324376af74c00", "generation_seconds_batch": 19.123189495061524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1089149713516235, "target_z": 0.8828125039837492, "ce": 5.657250881195068, "genuineness": 4.532451152801514, "identity": 0.4850270748138428, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/27fe535509ad649374f784f5dceecc14c181d03097cabd4e9e9579e526486df5.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "289a42c8fa97c8a284b916fe300d17f29e30b0c3f13611587bd035613861a4e7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "68e1e03a0cf0eeed84d34afba08a72f1ce6765af473758ee577e7db9dd71109d", "generation_seconds_batch": 19.15356204006821, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14594054222106934, "target_z": -0.49023435408531674, "ce": 5.919358730316162, "genuineness": 4.582659721374512, "identity": 0.7355597019195557, "hypothesis": "J'ai trouvé la 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_Disappointment/289a42c8fa97c8a284b916fe300d17f29e30b0c3f13611587bd035613861a4e7.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "2925ecaffb3529e5e4973a9e5a0106454916b0a23f36b85971f701b2eacf1d13", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "32ddf62ce9895de2c8079a30e86172891685a02323d34d206013ca404703e998", "generation_seconds_batch": 19.347304549999535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18155550956726074, "target_z": -0.4394531313076029, "ce": 5.831989288330078, "genuineness": 4.758388519287109, "identity": 0.7086943984031677, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2925ecaffb3529e5e4973a9e5a0106454916b0a23f36b85971f701b2eacf1d13.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "2992e46542942785a46b5736cb464dea20328851633f620e8350fc894e867083", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5589fe91682c9ee4ce4bddbaa15146d0f2fa24e97b33d0203947ae4f61640a5b", "generation_seconds_batch": 19.109445331036113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21443089842796326, "target_z": -0.39257810740510773, "ce": 6.109982967376709, "genuineness": 4.419482707977295, "identity": 0.4453352391719818, "hypothesis": "The 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_Disappointment/2992e46542942785a46b5736cb464dea20328851633f620e8350fc894e867083.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "2a599ceb8a9d07a372021538da236faf96a3e54e7b2c6c1750964d1949835ccc", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5a9ec1df2576292540c77df6e6fedc234ec435c13c3c525f575f513ee5f74c53", "generation_seconds_batch": 14.346919521107338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17607629299163818, "target_z": -0.44726561404468973, "ce": 5.9431867599487305, "genuineness": 4.7081804275512695, "identity": 0.4845097064971924, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2a599ceb8a9d07a372021538da236faf96a3e54e7b2c6c1750964d1949835ccc.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "2aa7cff256c0fe6b03055b20775757113962f99531bb8e44458796dd5f4823c5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6e9e403e669cac34ab05d64a29058d382fbf875ac5585b6633b2a5a30c68310b", "generation_seconds_batch": 19.24818728293758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18155550956726074, "target_z": -0.4394531313076029, "ce": 5.935244083404541, "genuineness": 4.796044826507568, "identity": 0.6413498520851135, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2aa7cff256c0fe6b03055b20775757113962f99531bb8e44458796dd5f4823c5.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": "2aba27ced91a872b351d5cbd9a5e0dc1c862f2838bad03765dc7e9c1ff3a58d2", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4a1f42a447effa37a3450a19427263522c54a18865e61347910e5b0980f56a8", "generation_seconds_batch": 14.55058903596364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2336081862449646, "target_z": -0.3652343753319791, "ce": 5.708878040313721, "genuineness": 4.6705241203308105, "identity": 0.6156260967254639, "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_Disappointment/2aba27ced91a872b351d5cbd9a5e0dc1c862f2838bad03765dc7e9c1ff3a58d2.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "2aec41ee22d24646251f23c924da2ed338d172ef632b39a4556108de7e8f4fab", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "598e29c15645f970c0c8efe831ab940952f4e1f9d0112d556bce09e7d381d18e", "generation_seconds_batch": 19.067818469018675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24867606163024902, "target_z": -0.3437500053116656, "ce": 5.387199878692627, "genuineness": 4.507347106933594, "identity": 0.55147784948349, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2aec41ee22d24646251f23c924da2ed338d172ef632b39a4556108de7e8f4fab.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": "2b43ae2223860fc84a2393b89edce46751b6dc0f4f398d558a4eb5c8901441a7", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14274283cbdda083c849e5f5827b2c1252d72ac9cb75f8e75f0de574c1b720e4", "generation_seconds_batch": 19.29645399702713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7294783592224121, "target_z": 0.34179684213406913, "ce": 6.054384231567383, "genuineness": 4.444586753845215, "identity": 0.3349434435367584, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2b43ae2223860fc84a2393b89edce46751b6dc0f4f398d558a4eb5c8901441a7.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "2b5ab64b9183928f930db5bf86dc972fda33e0041d69c0fe18995766700499a3", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9cff7e8920ded2f7d3db5e181145f0195749c548c5dcc94bce4519b60b8b326a", "generation_seconds_batch": 16.884379753959365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2514156699180603, "target_z": -0.33984376394312216, "ce": 6.125868320465088, "genuineness": 4.519899368286133, "identity": 0.6820535659790039, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2b5ab64b9183928f930db5bf86dc972fda33e0041d69c0fe18995766700499a3.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "2b9675bff92c0073a37240bba615fa8a95b76ae194abed1690806ee4810e8a22", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6923c930d82eee7054d072d3d8a901863c46d907c1e5c25e99085f18143c828a", "generation_seconds_batch": 20.166732070967555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2555251121520996, "target_z": -0.33398435939698234, "ce": 6.221180438995361, "genuineness": 4.909013748168945, "identity": 0.5875355005264282, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2b9675bff92c0073a37240bba615fa8a95b76ae194abed1690806ee4810e8a22.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "2b9d0989f7e7e49f245239bbc0c03e3692ab5c6a67945f64bc3c9a1b3b58dd6f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1b5367c404d0d44fcad9ddba3505e7205be5e9fe7f3480cbe67823ab6d44a304", "generation_seconds_batch": 22.60219835594762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24319683015346527, "target_z": -0.35156250929541477, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.27611982822418213, "hypothesis": "The 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_Disappointment/2b9d0989f7e7e49f245239bbc0c03e3692ab5c6a67945f64bc3c9a1b3b58dd6f.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "2bc3a60a02c58ac76a7c3da21a67f749d2dcf2240dddbabe01b74d1232e1ea06", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "76e0b30f270034357ff8ce3defe7e8302f94f984cbc37fddd5ad19f223ed4df5", "generation_seconds_batch": 19.012331202975474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18977436423301697, "target_z": -0.4277343647086479, "ce": 5.609594821929932, "genuineness": 4.570107460021973, "identity": 0.4051012098789215, "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_Disappointment/2bc3a60a02c58ac76a7c3da21a67f749d2dcf2240dddbabe01b74d1232e1ea06.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "2bea8ebd6c6da0fc4310791931886d71a4af2473ad207f050568477b28189df9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a293b9378208f0179950cc2b1b26772bbc8647e170f3444ba45edf44a275dfea", "generation_seconds_batch": 20.588070267927833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07608035206794739, "target_z": -0.5898437639431222, "ce": 6.062326908111572, "genuineness": 4.570107460021973, "identity": 0.7511453628540039, "hypothesis": "J'ai trouvé la 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_Disappointment/2bea8ebd6c6da0fc4310791931886d71a4af2473ad207f050568477b28189df9.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "2c055f2416896f67fbd0b9fd7c12da46243102a5565942939742e9f3cb8310b2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b645425db81df13e231ae7b4841129bde921f8cf3f98952138dfd3db6f1edc0e", "generation_seconds_batch": 14.211160989943892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14731034636497498, "target_z": -0.488281233401045, "ce": 6.149696350097656, "genuineness": 4.808597087860107, "identity": 0.4546816945075989, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2c055f2416896f67fbd0b9fd7c12da46243102a5565942939742e9f3cb8310b2.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "2c3bdc01becd752461780f44968ae927438d34fda046b8f3b857e2acdc7d38ba", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "58faaba0b71b750be6e774718c3bc29d0fb2305c07c044c9ed7d45a574409c95", "generation_seconds_batch": 19.007845676969737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24319683015346527, "target_z": -0.35156250929541477, "ce": 5.704906940460205, "genuineness": 4.570107460021973, "identity": 0.5563244819641113, "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_Disappointment/2c3bdc01becd752461780f44968ae927438d34fda046b8f3b857e2acdc7d38ba.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "2c75138e853b110bdabcfcd2e2f1345d905a08bb1aaed4413e61bd1072d1cc37", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "377710bd04ed6c0e51fa7cfb8272ff343f5603544164ed2b06599d49122231ed", "generation_seconds_batch": 15.822194532025605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1733366847038269, "target_z": -0.4511718554132331, "ce": 6.181467056274414, "genuineness": 4.337893962860107, "identity": 0.4918339252471924, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2c75138e853b110bdabcfcd2e2f1345d905a08bb1aaed4413e61bd1072d1cc37.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "2cd2f4e649974eb321b35c97ea38fd684224bfa1da772c6154e5653fe446550e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4914de13df04526af397043e9402b1297e452c67e88fd57f9e1860156e3dca67", "generation_seconds_batch": 20.01456618902739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18977436423301697, "target_z": -0.4277343647086479, "ce": 6.205295085906982, "genuineness": 4.394378662109375, "identity": 0.7370932102203369, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2cd2f4e649974eb321b35c97ea38fd684224bfa1da772c6154e5653fe446550e.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "2d22dd2f7df9d1254950c19699b6bdba49afc6acdf195436de020f9b19a7c195", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b8bd3cfc74abb23eaba3c213c64f58996a243d85684899137c54ff711815736f", "generation_seconds_batch": 19.349877258995548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25004586577415466, "target_z": -0.3417968846273939, "ce": 6.332377910614014, "genuineness": 4.7081804275512695, "identity": 0.6852477788925171, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2d22dd2f7df9d1254950c19699b6bdba49afc6acdf195436de020f9b19a7c195.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "2d272c4a20696831e70627634561b8b6496db6019d75e2b8a11205b84dbe88e7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "aa600213cf93c20e81050253ed14db96228d36bb7c7c6a36e0fe17805b1cd815", "generation_seconds_batch": 20.100321225007065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4555169343948364, "target_z": -0.04882814458676687, "ce": 5.816103935241699, "genuineness": 4.770940780639648, "identity": 0.7290928363800049, "hypothesis": "J'ai trouvé la 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_Disappointment/2d272c4a20696831e70627634561b8b6496db6019d75e2b8a11205b84dbe88e7.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "2d4f8fdb47c74439ba9b8a187edcf8a1487cb109f14eb9f8ff281b0630a11986", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2f5ef4b3b1e798e203578dd10c333dc6f01f9904014c1e3e43937f15fe77e1ab", "generation_seconds_batch": 16.266686766059138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19936299324035645, "target_z": -0.414062519918746, "ce": 6.0305562019348145, "genuineness": 4.532451152801514, "identity": 0.855310320854187, "hypothesis": "La porte 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_Disappointment/2d4f8fdb47c74439ba9b8a187edcf8a1487cb109f14eb9f8ff281b0630a11986.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "2da6309034259c7e3379d575579190b707a5af93dd29c05d55400e36e88e03ac", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3321b902e848dab7adac446869686c0675e7c0c56fb048c31aadbae3786a35c", "generation_seconds_batch": 19.44540380698163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6616729497909546, "target_z": 0.2451172195359831, "ce": 5.057579040527344, "genuineness": 4.532451152801514, "identity": 0.5778728127479553, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2da6309034259c7e3379d575579190b707a5af93dd29c05d55400e36e88e03ac.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": "2e211a2639cb1363bbbd969f972f9653383f0d81478a15a460fe3a3092482f19", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2252f85dcd384294918fb49efe8acaa13345f2c3e2e654284bec345713d532ea", "generation_seconds_batch": 14.799191789003089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.632906973361969, "target_z": 0.20410155768630306, "ce": 5.383228778839111, "genuineness": 4.406930446624756, "identity": 0.6415271162986755, "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_Disappointment/2e211a2639cb1363bbbd969f972f9653383f0d81478a15a460fe3a3092482f19.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "2e84e87cc645f313ae8adf7738917aa1ac23bf96ed5cdcdfc9f4592d958de2fa", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "79565ef906db2b9e36f750150570aae5d3bef4e7452b069e47e84881b2a530c3", "generation_seconds_batch": 19.731989415944554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2021026313304901, "target_z": -0.41015623605687784, "ce": 5.871703147888184, "genuineness": 4.7332844734191895, "identity": 0.5752619504928589, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2e84e87cc645f313ae8adf7738917aa1ac23bf96ed5cdcdfc9f4592d958de2fa.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": "2e8ec3c800292227b98b4619903fa594ab57b2a71deaa7b223c1737f2e31d4c7", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce7f2f812624c3bf80de475227629fb536ba89408edeb00d3d819b128fbbf869", "generation_seconds_batch": 19.537173637072556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4267509877681732, "target_z": -0.08984376394312217, "ce": 5.250188827514648, "genuineness": 4.413206577301025, "identity": 0.329961359500885, "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_Disappointment/2e8ec3c800292227b98b4619903fa594ab57b2a71deaa7b223c1737f2e31d4c7.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "2eed304966363eae092d9bdf022f2edfbf4a6e9e61087194838d111f48256805", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7cb5be5e24b31c8ee2b71769b5711555f72409202c5f012ea0cb2461277a3eef", "generation_seconds_batch": 14.211160989943892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18840456008911133, "target_z": -0.4296874853929196, "ce": 5.967014789581299, "genuineness": 4.7332844734191895, "identity": 0.46631699800491333, "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_Disappointment/2eed304966363eae092d9bdf022f2edfbf4a6e9e61087194838d111f48256805.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "2f5d26bc1327949d83e55d17ee88cd34955f1dcf33f6c5be26946d2a6edce0e5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "865fdc66bcee2d2914e2b257d1e50f53569be182a94e000798c7da8ce9c95626", "generation_seconds_batch": 22.335487043950707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4363396465778351, "target_z": -0.0761718766598955, "ce": 5.967014789581299, "genuineness": 4.413206577301025, "identity": 0.5212618708610535, "hypothesis": "ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2f5d26bc1327949d83e55d17ee88cd34955f1dcf33f6c5be26946d2a6edce0e5.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "2ff0e680ae30eabdc9455680c5507d89a4588efbe413590bb5c07dccf2714961", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e0ac8bc1f4cb1831029b21b42b28f6e3cc0b7c31ed8f7b39c2c3198f18fb89cf", "generation_seconds_batch": 19.102543856948614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3911360204219818, "target_z": -0.14062498672083604, "ce": 6.0146708488464355, "genuineness": 4.720732688903809, "identity": 0.5689598321914673, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/2ff0e680ae30eabdc9455680c5507d89a4588efbe413590bb5c07dccf2714961.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "30304f9e887d7b96b9fde23f6e2e241071b530718bea64f7f7d1c93ec23b114a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "33a7ef0276d3af2ea292ebc0b579bd2411f494100bbf634dc64f13b774150594", "generation_seconds_batch": 15.494035186013207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09525766968727112, "target_z": -0.5624999893766688, "ce": 6.0305562019348145, "genuineness": 4.7081804275512695, "identity": 0.5465534925460815, "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_Disappointment/30304f9e887d7b96b9fde23f6e2e241071b530718bea64f7f7d1c93ec23b114a.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "30a38fa0aa6a48d077c645690ddd14684fa67fefbf180b171210af604c01844b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7310aaeba2d47dd0ffd826a8aaa4a77af3dde82746ff8854d27fdb74406722b8", "generation_seconds_batch": 19.75656656001229, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.240457221865654, "target_z": -0.3554687506639582, "ce": 5.8875885009765625, "genuineness": 4.193545341491699, "identity": 0.6236052513122559, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/30a38fa0aa6a48d077c645690ddd14684fa67fefbf180b171210af604c01844b.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "30ed393b71f6ec257c4f9dbfee88d023826ea47aabab92ee7dd817d21177573e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "23aa82215ef9e9c19d6c531c81731ab2bf98d63f4cb403877d87928b2a3cb7c6", "generation_seconds_batch": 14.265144537086599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3842869699001312, "target_z": -0.15039063263551927, "ce": 5.605623245239258, "genuineness": 4.68307638168335, "identity": 0.7088704109191895, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/30ed393b71f6ec257c4f9dbfee88d023826ea47aabab92ee7dd817d21177573e.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "318150f3f296b9a00d860d44cbb416fd6cccb23e154fe67340f05efcd480b52f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a8a4a0184ff4cef3307ade5ec3e6ba142ce20dc5df712233ddcc795d98626f97", "generation_seconds_batch": 19.8159930909751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22812896966934204, "target_z": -0.37304685806906596, "ce": 6.165581703186035, "genuineness": 4.287685871124268, "identity": 0.5723704099655151, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/318150f3f296b9a00d860d44cbb416fd6cccb23e154fe67340f05efcd480b52f.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "318c50f6993d1a77f888da9d540e179f645355594583476719b5bd0d3aade81b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0c4568adf2cf9dd805b644d71b7110c2c9b5f7fadbc4d28dbabd2d3c8425d458", "generation_seconds_batch": 19.359982753987424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10073688626289368, "target_z": -0.554687506639582, "ce": 6.292664527893066, "genuineness": 4.532451152801514, "identity": 0.3557226061820984, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/318c50f6993d1a77f888da9d540e179f645355594583476719b5bd0d3aade81b.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "31ae28e102206c9e476d3e1cd2fe9ecaa05775b0248bd72d0522c621f5e78dec", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a8bd93110e6d4c694500127b323a53a656a4a6537b57b4f82d677e1d11497e4d", "generation_seconds_batch": 19.085748651996255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4514075219631195, "target_z": -0.05468750663958199, "ce": 5.911416053771973, "genuineness": 4.507347106933594, "identity": 0.3953045606613159, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/31ae28e102206c9e476d3e1cd2fe9ecaa05775b0248bd72d0522c621f5e78dec.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": "3236c56acefa9360a1be357bc1146f8b1668516e4681dc770a10ed7c0cb50f5b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b40df96496ee2d30afaf40457698b7e1f372851402698fc4c9165dcd96d336c", "generation_seconds_batch": 15.138412976055406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27881181240081787, "target_z": -0.30078126527103854, "ce": 5.903473377227783, "genuineness": 4.808597087860107, "identity": 0.6716846227645874, "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_Disappointment/3236c56acefa9360a1be357bc1146f8b1668516e4681dc770a10ed7c0cb50f5b.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": "324329035d88a3e508b919e8af15cf5bfabaf15f9279830c7c0695d63d0948cd", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87be25a686af6cb711db095171a22146bd8cf852c058498948f9edec85247844", "generation_seconds_batch": 14.52662561100442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1870347559452057, "target_z": -0.43164060607719135, "ce": 5.681078910827637, "genuineness": 4.6705241203308105, "identity": 0.6433095932006836, "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_Disappointment/324329035d88a3e508b919e8af15cf5bfabaf15f9279830c7c0695d63d0948cd.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "327a53f3289a39d3690e318f7aded0f1fb73f4f61b7d4e2db700f9c643a416ff", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b15a4f91757caaef93785ed3fc42a7d7d3b610e24af20dda5abf507aca3cd293", "generation_seconds_batch": 19.606533956946805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3185362219810486, "target_z": -0.24414063794718488, "ce": 6.078212261199951, "genuineness": 4.758388519287109, "identity": 0.8090286254882812, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/327a53f3289a39d3690e318f7aded0f1fb73f4f61b7d4e2db700f9c643a416ff.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "328522cd8946296b1c1214a38f234aa502120806d22abfc62a5bac12e68b84eb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "eedb8258baf855ba7a9dbf93f29fea91c1bdb10093f9c2b965f38ce1329c2af8", "generation_seconds_batch": 19.116041926085018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34182295203208923, "target_z": -0.2109375013279164, "ce": 5.363371849060059, "genuineness": 4.444586753845215, "identity": 0.6356335878372192, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/328522cd8946296b1c1214a38f234aa502120806d22abfc62a5bac12e68b84eb.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "3291ce6e8821dcbf17c368e558fc6822fc70ca01d15457b200813df38ffdc895", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "257f0e42853b5e120d5fc07b08169a555f46a1844f909adf2f27da5e03dece7c", "generation_seconds_batch": 18.75619635405019, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26100432872772217, "target_z": -0.3261718766598955, "ce": 6.070269584655762, "genuineness": 4.632867813110352, "identity": 0.20063258707523346, "hypothesis": "The 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_Disappointment/3291ce6e8821dcbf17c368e558fc6822fc70ca01d15457b200813df38ffdc895.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "329f45ce4ba685e9aab1febc8ba0f5685b684ad9b7f08412da41d19c6c9e7ff0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5ca0e367a896f843ba67b2a2c4d6b44a633785fe15ac0912a8f6f585ef5858ad", "generation_seconds_batch": 19.53927271196153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21443089842796326, "target_z": -0.39257810740510773, "ce": 5.2938737869262695, "genuineness": 4.720732688903809, "identity": 0.5631045699119568, "hypothesis": "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_Disappointment/329f45ce4ba685e9aab1febc8ba0f5685b684ad9b7f08412da41d19c6c9e7ff0.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "33083b88ce432f94d8ca9ea8364d1c328b903c7ebb7e141fe9deeb6aaa98ed46", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b46c756e0a9e7b501c3bd1fa98299e32d00c3ad460214f0b35749bf056d9a10e", "generation_seconds_batch": 20.204713333048858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6048259139060974, "target_z": 0.16406247742542124, "ce": 5.331601142883301, "genuineness": 4.582659721374512, "identity": 0.6404480338096619, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/33083b88ce432f94d8ca9ea8364d1c328b903c7ebb7e141fe9deeb6aaa98ed46.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "33260831c5c0bd184db6f6a1908968ea103ee0989d4690b23c69e8fbcccaf2d1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3f3aec7782f1bd26c993cc21fa4a7cf7531a7f8be144057aed981249d857edc2", "generation_seconds_batch": 19.196477279998362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43496984243392944, "target_z": -0.07812499734416721, "ce": 5.474569320678711, "genuineness": 4.413206577301025, "identity": 0.33496928215026855, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/33260831c5c0bd184db6f6a1908968ea103ee0989d4690b23c69e8fbcccaf2d1.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "3384fab5449d64bab97a62a6152e008305b36d0786ebe5bf36004167e36a11f8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f16fd9532c6e4adff7d8b91aa1d41d2033f1efc6ab1d299d9e3e749aed734dc1", "generation_seconds_batch": 21.387406038935296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17196685075759888, "target_z": -0.45312501859082954, "ce": 5.935244083404541, "genuineness": 4.519899368286133, "identity": 0.6087273359298706, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3384fab5449d64bab97a62a6152e008305b36d0786ebe5bf36004167e36a11f8.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "338dbbea302cb96ae01a8510d465afaa616e8c9b5825d18464998bb5a545be4d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "89df7a5a26ca64396dc03594c80d5ebff2acb70a38a03b4de25d02e3b5cdb7fa", "generation_seconds_batch": 20.60035069694277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23771759867668152, "target_z": -0.359375013279164, "ce": 6.221180438995361, "genuineness": 4.469690799713135, "identity": 0.6499641537666321, "hypothesis": "ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/338dbbea302cb96ae01a8510d465afaa616e8c9b5825d18464998bb5a545be4d.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "33a73b586416329c71f32030792bb03bd87d4d317ff4af3349dba74329aa5b35", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0444082c0168be636b637b9c77a4d3707389d7ec6d54a584e8b5603be129b543", "generation_seconds_batch": 14.245066997944377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2514156699180603, "target_z": -0.33984376394312216, "ce": 6.268836498260498, "genuineness": 4.331617832183838, "identity": 0.11816339194774628, "hypothesis": "The 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_Disappointment/33a73b586416329c71f32030792bb03bd87d4d317ff4af3349dba74329aa5b35.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "4170eebe09455e5514585d114e2dfc9f68af0449543162498a10035183300f0b", "generation_seconds_batch": 18.297199208056554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2555251121520996, "target_z": -0.33398435939698234, "ce": 6.133810997009277, "genuineness": 4.469690799713135, "identity": 0.7525497078895569, "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_Disappointment/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": "341fc749af248a41fdb1f290478cd1a0f70c38f0d7138adcc098c1fcf46d2f80", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3c07baf7ea91af98afbe380c8a757826e853ef9b5ca284e3f6519e64d39152f", "generation_seconds_batch": 19.503900429001078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24730625748634338, "target_z": -0.3457031259959373, "ce": 6.141753673553467, "genuineness": 4.457139015197754, "identity": 0.40387189388275146, "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_Disappointment/341fc749af248a41fdb1f290478cd1a0f70c38f0d7138adcc098c1fcf46d2f80.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "34681785d050585e212d9c78a8db31e177e58294dc1546d7db5e09696ca59d95", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "17ee212291a24e7669a29f49909f7fabe1a46689ee56b4f3dd90c344b9947faf", "generation_seconds_batch": 18.98531072505284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25689488649368286, "target_z": -0.33203128120603537, "ce": 5.879645347595215, "genuineness": 4.545003414154053, "identity": 0.4405502676963806, "hypothesis": "The 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_Disappointment/34681785d050585e212d9c78a8db31e177e58294dc1546d7db5e09696ca59d95.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "71c9e5469139d97eefd1d6f0660bbf53cbaa65c0a1709262580954b779e1cb49", "generation_seconds_batch": 14.307214510045014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21717050671577454, "target_z": -0.38867186603656434, "ce": 6.38003396987915, "genuineness": 4.105680465698242, "identity": 0.2742883563041687, "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_Disappointment/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "34da30c8302d1e6f854390512538348544d0a8d06ea65d29acb82b208a040669", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee216792ca4b3341ea6c7f580f05467ca1d46f0b8a79c188e1eb9e8c3437019c", "generation_seconds_batch": 19.449214715044945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25278550386428833, "target_z": -0.33789060076552574, "ce": 6.0305562019348145, "genuineness": 4.331617832183838, "identity": 0.3949705958366394, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/34da30c8302d1e6f854390512538348544d0a8d06ea65d29acb82b208a040669.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "3515fa0f81acfdf1f845a777a3f55dab14b7267a17745e9e7d920aebd6b1ef24", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e59d2d1db91591a7927ad1c3fd1e4f37194f20736755c8cbaa56a394337ca96e", "generation_seconds_batch": 14.074640545994043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22812896966934204, "target_z": -0.37304685806906596, "ce": 5.7247633934021, "genuineness": 4.545003414154053, "identity": 0.40421852469444275, "hypothesis": "The 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_Disappointment/3515fa0f81acfdf1f845a777a3f55dab14b7267a17745e9e7d920aebd6b1ef24.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "3534c8d636171f61f3c596cc4618ac44816fb2c7593153c1b5f097e97521a3d6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30bdd01eefebed428b7ea08c23108a6273b58e888f3d57632aadcae55242cba4", "generation_seconds_batch": 19.01168607699219, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21443089842796326, "target_z": -0.39257810740510773, "ce": 5.673136234283447, "genuineness": 4.507347106933594, "identity": 0.6725894808769226, "hypothesis": "La porte 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_Disappointment/3534c8d636171f61f3c596cc4618ac44816fb2c7593153c1b5f097e97521a3d6.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "35936abe523e481b5a860980c05348906ef46aa3f0943fd1d76647ff8316c80a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e809789e20af32655545b6807b2bf8dcb77bfb689292b2b2530667c8c1035a04", "generation_seconds_batch": 23.91424252500292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01854845881462097, "target_z": -0.6718750026558328, "ce": 6.3641486167907715, "genuineness": 4.444586753845215, "identity": 0.6460944414138794, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/35936abe523e481b5a860980c05348906ef46aa3f0943fd1d76647ff8316c80a.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": "35fbe7acd3a46bb59659ce7962ed6c6d59cf2aee06404cb60874db9f0e6bb68b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "92aef359d8539ca7343d6901f361fb0f57c2b384668eb8144f2fedfe55563708", "generation_seconds_batch": 14.401093303924426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41373783349990845, "target_z": -0.10839843169036575, "ce": 5.982900142669678, "genuineness": 4.519899368286133, "identity": 0.6382484436035156, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunchtoon.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/35fbe7acd3a46bb59659ce7962ed6c6d59cf2aee06404cb60874db9f0e6bb68b.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "3628e73521bde84c308cdd9d12e86a763ed57c5a3b13dbb27f676ac72b19f257", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "be3bcce1700ffd226ef2830e7c134cc93ba4f13f404e6f632f10fc873b91f14a", "generation_seconds_batch": 19.046880087000318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6185240149497986, "target_z": 0.18359376925478776, "ce": 5.982900142669678, "genuineness": 4.482243061065674, "identity": 0.700951337814331, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3628e73521bde84c308cdd9d12e86a763ed57c5a3b13dbb27f676ac72b19f257.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "3755e192e9c06325259d7417585f427b46711b54bfad5107941b11a54a95ae2c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ccd93d07a4afae89db06fbdec4ec24cd99544bd509b4c60de1580bebe076852c", "generation_seconds_batch": 19.158086092909798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.056903064250946045, "target_z": -0.6171874960162508, "ce": 5.855817794799805, "genuineness": 4.532451152801514, "identity": 0.5311691761016846, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3755e192e9c06325259d7417585f427b46711b54bfad5107941b11a54a95ae2c.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "37883bca0f82ce67f50526ceab0ee26db05b758ed44021b1eb7da4092a5393ef", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "12753532f971db52fe248f08e469473dda0a3676c4af97efd69fe9abece754d7", "generation_seconds_batch": 22.70765170804225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12539342045783997, "target_z": -0.5195312493360418, "ce": 6.157639026641846, "genuineness": 4.055472373962402, "identity": 0.4639670252799988, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/37883bca0f82ce67f50526ceab0ee26db05b758ed44021b1eb7da4092a5393ef.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "37b3a11558ed2ff665ede47166f8adf45612f500afc4a85ed4c3b9b766bd214d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a4d110061a7aed6d3b81247737e0150dec4336d3786e4a52b07bb4e4480034bf", "generation_seconds_batch": 19.442223489051685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6185240149497986, "target_z": 0.18359376925478776, "ce": 5.462655067443848, "genuineness": 4.281409740447998, "identity": 0.40795841813087463, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/37b3a11558ed2ff665ede47166f8adf45612f500afc4a85ed4c3b9b766bd214d.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "387ea4abd3c1987a02e3a8d599e12f46c5dc09fc5cb3082c068e00afd8f51eda", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "52e608029109e236938010cd63d0e480e3ab50ae301a409a91a8a998b99e9473", "generation_seconds_batch": 20.013352900976315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11991420388221741, "target_z": -0.5273437320731287, "ce": 6.395919322967529, "genuineness": 4.557555198669434, "identity": 0.5785884261131287, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/387ea4abd3c1987a02e3a8d599e12f46c5dc09fc5cb3082c068e00afd8f51eda.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "3886ca322ee8f9929b506ae6c59aa678cdfd5184fb86448625e5bd3e0cd1c959", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c5fd98ddcd0acbebc421c496516df1c1a8c373c2e00ccfad50c412b059c38991", "generation_seconds_batch": 19.226010998012498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27470239996910095, "target_z": -0.3066406273238537, "ce": 5.661221981048584, "genuineness": 4.68307638168335, "identity": 0.7739530801773071, "hypothesis": "La porte 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_Disappointment/3886ca322ee8f9929b506ae6c59aa678cdfd5184fb86448625e5bd3e0cd1c959.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": "39d0368167c07981dceba2495382678ff1d07b00b0e62ef3ba9a8a6253b689f3", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c51b01ec3d4fe531f1671a1a915c845753014433780f852439ccf7a430206b6", "generation_seconds_batch": 15.272111283964477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.525377094745636, "target_z": 0.050781222777713846, "ce": 5.518253803253174, "genuineness": 4.582659721374512, "identity": 0.8120901584625244, "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_Disappointment/39d0368167c07981dceba2495382678ff1d07b00b0e62ef3ba9a8a6253b689f3.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "39e8225d176e3e3699ab2d280cb3ce26c702107eb4d210a051b33066babdc823", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8e94b926fc27020f4239c5715d3d737877d931f7d8c7509551abff2a782fabe0", "generation_seconds_batch": 19.31072629999835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2938796877861023, "target_z": -0.27929689525072504, "ce": 5.839932441711426, "genuineness": 4.7458367347717285, "identity": 0.42107176780700684, "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_Disappointment/39e8225d176e3e3699ab2d280cb3ce26c702107eb4d210a051b33066babdc823.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "39fd4d6271a1082fa9bd747c7111c6778d967d96e57a39d30e1f5094dee6041d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b1d95d27ccc69c49ea67ab9a673a549e4928869f7db8e71ee8efe622c6578296", "generation_seconds_batch": 19.30819051002618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3514115810394287, "target_z": -0.19726565653801445, "ce": 6.038498878479004, "genuineness": 4.595211505889893, "identity": 0.6280087232589722, "hypothesis": "De deur staat nog open. Ik heb je jas op gewoon 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_Disappointment/39fd4d6271a1082fa9bd747c7111c6778d967d96e57a39d30e1f5094dee6041d.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "3a0c7688938453c6602f3f2cf4fd3a8f73046f2c90dd510b803af7d4aefd7afd", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "edbecfff3d95d058fd595bb17838b082f1f40e63e54f88529c6afa0619f9b5ad", "generation_seconds_batch": 19.18494679708965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4911319315433502, "target_z": 0.0019531206842717077, "ce": 5.895530700683594, "genuineness": 4.896461486816406, "identity": 0.7563117742538452, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3a0c7688938453c6602f3f2cf4fd3a8f73046f2c90dd510b803af7d4aefd7afd.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "3a6bb73a2b07d0fa6e8e1540f5828d295f8254187d39f889cf141976a3ee44eb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4607edf7e43542e233fd07b61b1f882ac3bb9bd12881f318f21bcfe735898d3f", "generation_seconds_batch": 14.222704694024287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42401137948036194, "target_z": -0.0937500053116656, "ce": 5.645336627960205, "genuineness": 4.632867813110352, "identity": 0.562753438949585, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime, ¿cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3a6bb73a2b07d0fa6e8e1540f5828d295f8254187d39f889cf141976a3ee44eb.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "3a82ccf7b4462120898338735efdfa1b3368e6a2d805f302b112e5305b18a58e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0e4c15097047c19e58c8f81d2a70a0efa2f87c063c398547f19c3b4cdc2d5289", "generation_seconds_batch": 19.04896215593908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1198734045028687, "target_z": 0.8984374694579229, "ce": 6.022613525390625, "genuineness": 4.6956281661987305, "identity": 0.40081363916397095, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3a82ccf7b4462120898338735efdfa1b3368e6a2d805f302b112e5305b18a58e.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "3a8db08ea83e5ca14fc7ad0d42676f6d725d917052b05df9336d17ebc6810f37", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7661776e270f3e6ec4e6dd65ec49640008290590c3ce16d202cd20287f049ab5", "generation_seconds_batch": 23.968709630076773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 6.395919322967529, "genuineness": 4.557555198669434, "identity": 0.2767047882080078, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3a8db08ea83e5ca14fc7ad0d42676f6d725d917052b05df9336d17ebc6810f37.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "3ab8c97b899ffda25104300c20b5eae4afa6a6a7240dab8a7275d8d4ecb2bc0c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2653189f063a87f7c0f68dbca4b41e5783988a120427d70739f31a9be0af0182", "generation_seconds_batch": 19.105153116979636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24730625748634338, "target_z": -0.3457031259959373, "ce": 5.673136234283447, "genuineness": 4.457139015197754, "identity": 0.3709813356399536, "hypothesis": "The 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_Disappointment/3ab8c97b899ffda25104300c20b5eae4afa6a6a7240dab8a7275d8d4ecb2bc0c.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "3af51c929adcaa0849e91e20adf7ae441a8c5bf08034ea17d1a9aab64a051690", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2c03088ebaf7a8a37d5a38b509a41cf8e81fcf00e2a530d91036d97fb2ec95a0", "generation_seconds_batch": 17.668881096993573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3007287383079529, "target_z": -0.2695312493360418, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.7875210046768188, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3af51c929adcaa0849e91e20adf7ae441a8c5bf08034ea17d1a9aab64a051690.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "3b16d3a18bc5737ceb80a076711b4708b1f3edb58a5b9f0eb3c1d6256dfb234c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1996ff7da782bdc7905501290defc444bcacdfe7e026cfe3174982d1515a1e0f", "generation_seconds_batch": 22.265932583017275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0130283832550049, "target_z": 0.7460936311514824, "ce": 6.24500846862793, "genuineness": 4.419482707977295, "identity": 0.6030790209770203, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3b16d3a18bc5737ceb80a076711b4708b1f3edb58a5b9f0eb3c1d6256dfb234c.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "3b1724a9f33975aa5bec328d3a7d4543d543677d1c563b2d4784f52b888e788b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c5762c9c02f327fbd9bc856478aa25145ca1c6156a7823230cb8291dbce74ec7", "generation_seconds_batch": 15.83956362400204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1582687795162201, "target_z": -0.4726562679268714, "ce": 5.637393951416016, "genuineness": 4.607763767242432, "identity": 0.5277150869369507, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3b1724a9f33975aa5bec328d3a7d4543d543677d1c563b2d4784f52b888e788b.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "3b5f4525d127963cf13eda9390ba9ec19ac3d52b77ef0d2e128e1a83e6c8695b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7cb6ded3a669bdca8e5a0bae2f47ba5cdb1ed794435e6f4199472d335f61fec6", "generation_seconds_batch": 14.387616464984603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5000357031822205, "target_z": 0.014648468872024893, "ce": 6.022613525390625, "genuineness": 4.482243061065674, "identity": 0.5646274089813232, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3b5f4525d127963cf13eda9390ba9ec19ac3d52b77ef0d2e128e1a83e6c8695b.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": "3b98ef1b00d73da870e833eaaae68951c8bde045f1b62b5bef406bcfc9f2d253", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24f328462acadc27da06d5181f5c64c981c0714626df4030c66c0f5383aa8edf", "generation_seconds_batch": 19.491346533992328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2089516520500183, "target_z": -0.4003906326355193, "ce": 5.80021858215332, "genuineness": 4.532451152801514, "identity": 0.7580081224441528, "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_Disappointment/3b98ef1b00d73da870e833eaaae68951c8bde045f1b62b5bef406bcfc9f2d253.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "3bb6e525841f5ff27380d7f193b2a4dfa30e63feeda848e28b0da3b54e0555d9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "99f285ce1e0c28014edf266a7118d0e73acccce7b83bb681479431dcfa4f3742", "generation_seconds_batch": 19.751192939002067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 6.2767791748046875, "genuineness": 4.570107460021973, "identity": 0.35502830147743225, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3bb6e525841f5ff27380d7f193b2a4dfa30e63feeda848e28b0da3b54e0555d9.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "3bd14cc1a6b794dc06399bf420a4d208be89c75d81d3775e2fab0f2104d09a8c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f0146882f8d1904f9849409859b6acb36e8eefe12761edfefb35dd5ab4782dfb", "generation_seconds_batch": 19.646597373997793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23086857795715332, "target_z": -0.3691406167005225, "ce": 5.982900142669678, "genuineness": 4.896461486816406, "identity": 0.7448866367340088, "hypothesis": "J'ai trouvé la 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_Disappointment/3bd14cc1a6b794dc06399bf420a4d208be89c75d81d3775e2fab0f2104d09a8c.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "de096cafb0efc5fb2e65ab79b9ef458227651843294e51a967856c9738d03214", "generation_seconds_batch": 18.378899276955053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15415936708450317, "target_z": -0.4785156299796865, "ce": 6.181467056274414, "genuineness": 4.369274139404297, "identity": 0.5112227201461792, "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_Disappointment/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.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": "3cdfba4f55e02fafb2c57e9612ddefe8ad688f0c9366de2243c563a13050ed2e", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b82d90ded3f55426ec436d1da563358ae91d39dde21fe045b820a382ab39efb5", "generation_seconds_batch": 14.3944423670182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15004995465278625, "target_z": -0.4843749920325016, "ce": 5.927301406860352, "genuineness": 4.557555198669434, "identity": 0.33309733867645264, "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_Disappointment/3cdfba4f55e02fafb2c57e9612ddefe8ad688f0c9366de2243c563a13050ed2e.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": "3d4171f62368d95e7d58f6fc47820e10c67ce4ef31e04354f276b0342e8edfb6", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "493c1a93182ba7792df02fcedb828b0faf1718f4399fd1d8d8cf36373d07deeb", "generation_seconds_batch": 20.399317879928276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5020903944969177, "target_z": 0.017578128651770095, "ce": 5.764476776123047, "genuineness": 4.557555198669434, "identity": 0.5120806694030762, "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_Disappointment/3d4171f62368d95e7d58f6fc47820e10c67ce4ef31e04354f276b0342e8edfb6.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": "3e14730038cb29be15ae30f8743145c391909981491b6c3c5ce6af66977a4156", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b7ae6ad6dd63191aae0d65f3e94013e35c9e50004fc013e31c625c251164573", "generation_seconds_batch": 14.482510081026703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.269223153591156, "target_z": -0.31445315255426526, "ce": 5.4666266441345215, "genuineness": 4.7081804275512695, "identity": 0.8249996900558472, "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_Disappointment/3e14730038cb29be15ae30f8743145c391909981491b6c3c5ce6af66977a4156.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "3e2240a27c2fdbac8a66b760baf0eaf8c333843692f4cef0ee8160c99b6d88f5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "24f5a68bedde8bc55f5ab121197936cdcf4033d5b22b8767c2e5b1aa7cefd4f7", "generation_seconds_batch": 19.51532984606456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45962637662887573, "target_z": -0.04296874004062702, "ce": 5.375286102294922, "genuineness": 4.557555198669434, "identity": 0.8162298202514648, "hypothesis": "J'ai trouvé la 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_Disappointment/3e2240a27c2fdbac8a66b760baf0eaf8c333843692f4cef0ee8160c99b6d88f5.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "3e608055e6a8f80832d1f67aa6ee9e2663740d859c2e62e4a53a9e2028391f97", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9ef7567d51f5cdfbc63da1e3e7e53a16fbf392dbcfa9018278b8433ae7881c32", "generation_seconds_batch": 19.19308620505035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7993385791778564, "target_z": 0.4414062944851993, "ce": 6.006728172302246, "genuineness": 4.519899368286133, "identity": 0.7054498791694641, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3e608055e6a8f80832d1f67aa6ee9e2663740d859c2e62e4a53a9e2028391f97.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": "3f7b3b67c86d0600d76b3a44620510c59e068dd1b289b87978abac7d079ccba7", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "acbd3e32e8b49f53d04c6c4c4e68a5311fbbfb8e56cfeb3b4493fcdc13744927", "generation_seconds_batch": 15.056082320981659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24319683015346527, "target_z": -0.35156250929541477, "ce": 5.371314525604248, "genuineness": 4.545003414154053, "identity": 0.6860699653625488, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue, elle était d'ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3f7b3b67c86d0600d76b3a44620510c59e068dd1b289b87978abac7d079ccba7.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": "3f819fc308e5237ea6d51c606cbc400ef3ffd4bd4d7d637c0d56f64309303335", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "600d6380acb784ce94812f4cb2e74f896b6da938032eaf5a62296676f33ea3a2", "generation_seconds_batch": 14.480976433958858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5801286697387695, "target_z": 1.5546875491329066, "ce": 5.824047088623047, "genuineness": 4.532451152801514, "identity": 0.20955753326416016, "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_Disappointment/3f819fc308e5237ea6d51c606cbc400ef3ffd4bd4d7d637c0d56f64309303335.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": "3f8fd46e7f6435be63fc269944113ce9a0882d973b3fe810c9548b93a6eae0e3", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "95e9a69842cf5d9b0bae68ceb5844838a34cd3ddc996950e8ab26332fc36bc21", "generation_seconds_batch": 15.272111283964477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48154327273368835, "target_z": -0.011718766598954971, "ce": 5.43088436126709, "genuineness": 4.482243061065674, "identity": 0.8114242553710938, "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_Disappointment/3f8fd46e7f6435be63fc269944113ce9a0882d973b3fe810c9548b93a6eae0e3.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "3f956018f9e9ac9b504806b1e6d803e59eae1bf29ac8933196a51366096b9ae7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "daa0beaeb9d572c6e54d7e5b8af1873442351f4076acc09668d0c7a3ac03ac50", "generation_seconds_batch": 19.16944828699343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.419901967048645, "target_z": -0.09960936736448071, "ce": 5.700935363769531, "genuineness": 4.909013748168945, "identity": 0.6482345461845398, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3f956018f9e9ac9b504806b1e6d803e59eae1bf29ac8933196a51366096b9ae7.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "3fe622e9cfb7ab50e5cfd4913fe48d86cd2623985e47f5aa30c2811fd5bd088a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4c88c7e52ffb9459890b245a4672458a806ec5b7698e9aea624b16f5a2262596", "generation_seconds_batch": 19.35393814300187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08977842330932617, "target_z": -0.5703125146070803, "ce": 6.316492557525635, "genuineness": 4.7081804275512695, "identity": 0.47601354122161865, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/3fe622e9cfb7ab50e5cfd4913fe48d86cd2623985e47f5aa30c2811fd5bd088a.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": "3ffe5d6e7d932248b079d248d0f3a94d31ba36ae57e23a5109d9cf4dc6a6c5f9", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a6e866d6faf927f1858e289f94edb22dce9af7495b9824f1ad1916229a5091f", "generation_seconds_batch": 14.809686066000722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.103435754776001, "target_z": 0.8750000212466623, "ce": 5.518253803253174, "genuineness": 4.413206577301025, "identity": 0.567084550857544, "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_Disappointment/3ffe5d6e7d932248b079d248d0f3a94d31ba36ae57e23a5109d9cf4dc6a6c5f9.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "406457eda9197d1042dc761e7c0025f104ee9dba0c3871c9b9eb01cbc062936e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "25373cae11401e1d0a1d76696b386bf2e11b3add99cac984953c738bb89c34f2", "generation_seconds_batch": 19.09152650204487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7472858428955078, "target_z": 0.3671874535229261, "ce": 5.260117053985596, "genuineness": 4.545003414154053, "identity": 0.5490272045135498, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/406457eda9197d1042dc761e7c0025f104ee9dba0c3871c9b9eb01cbc062936e.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": "40cdb460defbfedc406b6d30bcae18ae483530e38c7c0466143fd366b22bfdca", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "474e7ea7b45425f4642e9d145a78bf62192bec01b703053e500a46c402fe93b2", "generation_seconds_batch": 14.43142698390875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17470648884773254, "target_z": -0.44921873472896146, "ce": 5.792276382446289, "genuineness": 4.193545341491699, "identity": 0.42829400300979614, "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_Disappointment/40cdb460defbfedc406b6d30bcae18ae483530e38c7c0466143fd366b22bfdca.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": "413ebddbdd9d74dca40241fb7e7669e0a63bd205967abefa74b3779083fd8261", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a6f2670025549cf3a74d9aa2ae4a7363bd99c957aa5e46f0fe4e636d3e732905", "generation_seconds_batch": 14.641394773032516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1719260215759277, "target_z": 0.9726561404468972, "ce": 5.80021858215332, "genuineness": 4.7081804275512695, "identity": 0.7384822368621826, "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_Disappointment/413ebddbdd9d74dca40241fb7e7669e0a63bd205967abefa74b3779083fd8261.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": "4167e170c90b28a55b065c32355cd59fb2214b3528bfc0de3f9fc6e6222c4ceb", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "59556bad1c034c509d4db1f0b1b5aa00a9d377a67c7c4cece9175c661508e7dc", "generation_seconds_batch": 15.424835161073133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4719546437263489, "target_z": -0.025390611388856923, "ce": 5.669164657592773, "genuineness": 4.645420074462891, "identity": 0.5756151080131531, "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": 0.120000000000001, "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_Disappointment/4167e170c90b28a55b065c32355cd59fb2214b3528bfc0de3f9fc6e6222c4ceb.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": "41d886a5478bfcddbb1f1fb50084574bfd8df2d401ad473bf31ac7afe4c82ff6", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f67ed0e9191f122be1e8639e8ba47e87ad5b00c761571fce22b754f3c2530469", "generation_seconds_batch": 14.510121461004019, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2829212546348572, "target_z": -0.29492186072489873, "ce": 6.268836498260498, "genuineness": 4.65797233581543, "identity": 0.4757729768753052, "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_Disappointment/41d886a5478bfcddbb1f1fb50084574bfd8df2d401ad473bf31ac7afe4c82ff6.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "422078e1f6aaf988ff1465387d93668d3ae1de5f3c4e85e583271d7d655ec7e8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5e9290ba2d15dfda860c073b554b87d29022cd67714ef83cb24e4c532f96b11d", "generation_seconds_batch": 21.387406038935296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15963861346244812, "target_z": -0.47070310474927496, "ce": 5.8875885009765625, "genuineness": 4.293961524963379, "identity": 0.3901924788951874, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/422078e1f6aaf988ff1465387d93668d3ae1de5f3c4e85e583271d7d655ec7e8.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "42676539f8dce48eab4b3499dd9375435d67562668bac74c8ad73df00f807fb6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4edf92e26f7d22b5c5bdcf8a095f2f8982b5cfbddaa86f0596b9eb8afa4f14a1", "generation_seconds_batch": 14.303154492983595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1089557409286499, "target_z": -0.542968740040627, "ce": 6.348263263702393, "genuineness": 4.833701133728027, "identity": 0.3761145770549774, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/42676539f8dce48eab4b3499dd9375435d67562668bac74c8ad73df00f807fb6.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "42702f2d2f496d3f4bbd5ba3a72e2447e7f2bbaf971f77f76b39421b2bda7fcc", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d665a645ab81bf0e5eaa23f6fbb077b6ea5b1de4046aedb854c23b53bb617668", "generation_seconds_batch": 19.123856881051324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2801816463470459, "target_z": -0.2988281020934421, "ce": 5.855817794799805, "genuineness": 4.758388519287109, "identity": 0.7748107314109802, "hypothesis": "La porte 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_Disappointment/42702f2d2f496d3f4bbd5ba3a72e2447e7f2bbaf971f77f76b39421b2bda7fcc.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "42adb094c03fb6e9b5b211df684db87e2887f37c4ce6a828ffcbc76f6a3a8466", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7c366d9c5c9f43d386709cdbbc5c9f5684299cadbe6fd60ad747e9995d8f2ed4", "generation_seconds_batch": 15.494035186013207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1445707082748413, "target_z": -0.49218751726291315, "ce": 6.316492557525635, "genuineness": 4.7332844734191895, "identity": 0.4695432484149933, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/42adb094c03fb6e9b5b211df684db87e2887f37c4ce6a828ffcbc76f6a3a8466.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "42be0007e9fa84fd2320a1335568c8131486266940adec7c23749cf4031730a5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d405b962a15a0d87fd6c26a63cc86ffb371367a4acd06aad455c579d5b758d4c", "generation_seconds_batch": 19.004502539988607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24730625748634338, "target_z": -0.3457031259959373, "ce": 6.062326908111572, "genuineness": 4.425758361816406, "identity": 0.6774976253509521, "hypothesis": "The 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_Disappointment/42be0007e9fa84fd2320a1335568c8131486266940adec7c23749cf4031730a5.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "4304c80c58eedd1750f5b7671e2ca838ab7858371299c39f91c0e745e8c12396", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f1760358e96065e7ff77bbbe5aaa79d993c819b28129c29360969b90793a83bc", "generation_seconds_batch": 19.159893534961157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7637235522270203, "target_z": 0.390624986720836, "ce": 5.7128496170043945, "genuineness": 4.143336772918701, "identity": 0.489383339881897, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4304c80c58eedd1750f5b7671e2ca838ab7858371299c39f91c0e745e8c12396.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "4346bc1b89ae85988a3da5c31155d1ce4945561d7a2d843a99869f04932e13f4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd2bf76083b625eb2aafb83ed2afc1344f31cf5eb9a7e3d7277ec7b7e9a2e992", "generation_seconds_batch": 16.266686766059138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21443089842796326, "target_z": -0.39257810740510773, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.7204341888427734, "hypothesis": "La porte 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_Disappointment/4346bc1b89ae85988a3da5c31155d1ce4945561d7a2d843a99869f04932e13f4.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "477c500bd5a4091434a11df67adf8cd8d66d41320c5b3ce559af78c0a8cb5d1e", "generation_seconds_batch": 18.297199208056554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1870347559452057, "target_z": -0.43164060607719135, "ce": 6.022613525390625, "genuineness": 4.300237655639648, "identity": 0.5404704809188843, "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_Disappointment/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "af49aad892396c41a31ee69a50f56e41bb2caa1513dd8a954f98398d104f1426", "generation_seconds_batch": 15.76232750795316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20758184790611267, "target_z": -0.402343753319791, "ce": 6.205295085906982, "genuineness": 4.607763767242432, "identity": 0.6561563611030579, "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_Disappointment/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.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": "44a0c3a3c2722dcf6e31b6ff8f09937155d4fe44469aa03efa92ec7df038f1b8", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "162b46ddb49500ada71c99dd699395c03309de4594eab8a699cfec61ce689e67", "generation_seconds_batch": 19.537173637072556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36373984813690186, "target_z": -0.17968752788624434, "ce": 6.141753673553467, "genuineness": 4.6956281661987305, "identity": 0.4649754762649536, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know and we can talk.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/44a0c3a3c2722dcf6e31b6ff8f09937155d4fe44469aa03efa92ec7df038f1b8.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "44f2f40c48121242dff71c63f3bb51f8247771c4b0721af7c83695c5bf016921", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c975e2e738694cbef094ab629a8b22a783bca644ea519006a7718f48e5464c0c", "generation_seconds_batch": 19.160312504973263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34593236446380615, "target_z": -0.20507813927510127, "ce": 5.4944257736206055, "genuineness": 4.7332844734191895, "identity": 0.783485472202301, "hypothesis": "J'ai trouvé la 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_Disappointment/44f2f40c48121242dff71c63f3bb51f8247771c4b0721af7c83695c5bf016921.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "45416a4315c302c039880f8d0ae1b69e18acd05622fd001b30993951f1524c15", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "694ac0fb305956894d97289acd1d379ddbe283a7d05db575fb3f5d0266e3705d", "generation_seconds_batch": 19.425936658051796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1089557409286499, "target_z": -0.542968740040627, "ce": 6.221180438995361, "genuineness": 4.6705241203308105, "identity": 0.7399405837059021, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/45416a4315c302c039880f8d0ae1b69e18acd05622fd001b30993951f1524c15.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "45e470d358ee590749ca3756315544dded45f9ee5d02a27a200bdcaa3cc2b563", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fb33e77cd75a840f9c569abb3889605e9b42c20bec9f2067333c220f21cf60e3", "generation_seconds_batch": 19.207481314078905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.590442955493927, "target_z": 0.14355468899390594, "ce": 6.23706579208374, "genuineness": 4.457139015197754, "identity": 0.6736622452735901, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/45e470d358ee590749ca3756315544dded45f9ee5d02a27a200bdcaa3cc2b563.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "f9df7c863ddf1aa6bfca010e5965dad8cc18f39cc4ab682fa5d2e4ad0b4459a1", "generation_seconds_batch": 14.686014799051918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02402767539024353, "target_z": -0.664062519918746, "ce": 6.324435234069824, "genuineness": 3.8169827461242676, "identity": 0.7137410044670105, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "462616dcc370046e66b2156243a3ba5cc43880f7a0483f7d07507079e1e5ded0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "aeefdcefdddd67fe6660b7ec25f20e15f9c927ce2000997e7326e13894aaa9e9", "generation_seconds_batch": 19.380403013899922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6171541810035706, "target_z": 0.18164060607719135, "ce": 5.732706069946289, "genuineness": 4.632867813110352, "identity": 0.7495324015617371, "hypothesis": "J'ai trouvé la 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_Disappointment/462616dcc370046e66b2156243a3ba5cc43880f7a0483f7d07507079e1e5ded0.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "463a178807e64fb76b49a42d03dc0801e00b38038756feddb30be4ebdce0260b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a0f4e7d25cda067bb7ec5caf4ea15880cfbf87563566ecbb3ced1a194ed679d", "generation_seconds_batch": 14.38312038499862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3431927561759949, "target_z": -0.2089843806436447, "ce": 5.816103935241699, "genuineness": 4.946669578552246, "identity": 0.8340309858322144, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt. Adieu.", "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_Disappointment/463a178807e64fb76b49a42d03dc0801e00b38038756feddb30be4ebdce0260b.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "46d9b6cd438e8b8e409cf6cf06b7d1c58d55982acc144c344e281f3b2be972a6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "65918feadf3a9fa8c9922eb22076877e6345735b8d65e620d8cfd9f739cb6f03", "generation_seconds_batch": 19.15581754501909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09525766968727112, "target_z": -0.5624999893766688, "ce": 6.046441555023193, "genuineness": 4.909013748168945, "identity": 0.6788330078125, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/46d9b6cd438e8b8e409cf6cf06b7d1c58d55982acc144c344e281f3b2be972a6.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": "46fac29e1a9369a08d7500cce390daca04771b00a2ed2b114253dd6851c52512", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6690d43c2d862a982b8f3acbb2bafc988db193186b0db5e4964ae01fc3bc62f6", "generation_seconds_batch": 15.1648919750005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29250991344451904, "target_z": -0.2812499734416721, "ce": 5.720792293548584, "genuineness": 4.758388519287109, "identity": 0.7599071860313416, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir. Puis près de la fenêtre, prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/46fac29e1a9369a08d7500cce390daca04771b00a2ed2b114253dd6851c52512.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": "47386d64049e1d9e75f1e8cf97b453ca5d43a1ada091cc94a3d4ff6f2cfea93e", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c225b6c7baa2f550a4eb3a824505462860244caf42e4fedf49e990588bfc936", "generation_seconds_batch": 19.408722269930877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5294865369796753, "target_z": 0.05664062732385369, "ce": 5.561938762664795, "genuineness": 4.494794845581055, "identity": 0.6674020290374756, "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_Disappointment/47386d64049e1d9e75f1e8cf97b453ca5d43a1ada091cc94a3d4ff6f2cfea93e.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "478ab2c011862815c85487b5b005fff358659eafd9e094054b266c3251ecd2bb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6cdb1df2ca0084f12e5aeeeeb45fe3d568808ea3970a6273cdb14716dc4ddcc7", "generation_seconds_batch": 15.234508499968797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17881590127944946, "target_z": -0.4433593726761463, "ce": 6.229123115539551, "genuineness": 4.7332844734191895, "identity": 0.4138525426387787, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/478ab2c011862815c85487b5b005fff358659eafd9e094054b266c3251ecd2bb.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "ce8f3dad9cfd723f806f93a32f02f3f9b6fcf712d3a234163b8ab9fcf52dae66", "generation_seconds_batch": 14.497203449020162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14183109998703003, "target_z": -0.4960937586314566, "ce": 6.070269584655762, "genuineness": 4.570107460021973, "identity": 0.6309787034988403, "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_Disappointment/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "47e3086f90eb8b2cc11bbcc865b8f78e06fa1da6c3bcd4868bc09cb44109437e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8685f9597a49332fcd34c7bb8c58860d46ccb937cd32c2461fb7ebb97c3dc1ac", "generation_seconds_batch": 19.130495981080458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3596304655075073, "target_z": -0.18554684744573474, "ce": 6.0305562019348145, "genuineness": 4.7332844734191895, "identity": 0.38807761669158936, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/47e3086f90eb8b2cc11bbcc865b8f78e06fa1da6c3bcd4868bc09cb44109437e.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "47e5bda47b3d4a2834340187815b1b54303039dcffaa87e5a252240d53655a86", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "104f0f05fa8754b59f681b84320f2d5e4eb83fbad444af51ea2b07ac2455681b", "generation_seconds_batch": 19.658303936943412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2760722041130066, "target_z": -0.304687506639582, "ce": 6.0305562019348145, "genuineness": 4.68307638168335, "identity": 0.8236092329025269, "hypothesis": "La porte est. La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/47e5bda47b3d4a2834340187815b1b54303039dcffaa87e5a252240d53655a86.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "47fbcc261c27cc5683ebea0a5ebf68b1bd1d88e40f709f21d22af9bbb205f18b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7606cad9177958af683c588ab7267439409828b4db5502074b8c147ee828a856", "generation_seconds_batch": 19.109445331036113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17196685075759888, "target_z": -0.45312501859082954, "ce": 6.1894097328186035, "genuineness": 4.268857479095459, "identity": 0.3894643187522888, "hypothesis": "The 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_Disappointment/47fbcc261c27cc5683ebea0a5ebf68b1bd1d88e40f709f21d22af9bbb205f18b.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "47ff3480a3269b2656f08f4fc847b77f67f2eda34ed1de2d933a6cd81e543b40", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6af65f34e65cbbe1dcea6e8ef97e3b52f7901a1a0304fbebb9a0028e5f01f8a4", "generation_seconds_batch": 19.332624329952523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6014013886451721, "target_z": 0.1591796544680796, "ce": 5.895530700683594, "genuineness": 4.833701133728027, "identity": 0.6994799375534058, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/47ff3480a3269b2656f08f4fc847b77f67f2eda34ed1de2d933a6cd81e543b40.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "4808d71e74ce8fd920d001d27bcdc547f0a2a2b39b7764276e8c8164e21f9b34", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a77978cab05e56159ec1ed41c40086a73a5cb9dbe9b3c77f3a54086fd06813c8", "generation_seconds_batch": 16.76668018696364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4185321629047394, "target_z": -0.10156248804875243, "ce": 6.0146708488464355, "genuineness": 4.7332844734191895, "identity": 0.5382750034332275, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4808d71e74ce8fd920d001d27bcdc547f0a2a2b39b7764276e8c8164e21f9b34.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": "48de400e45c461f5897a041672ea7b1cc66652b0fa21a0c5fffb1703df219d5c", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54b7a6477416f471a445b27e68afa6df938a6dbc672c9e5aaa6bbac87afa893e", "generation_seconds_batch": 14.526228441973217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4938715398311615, "target_z": 0.005859362052815124, "ce": 5.605623245239258, "genuineness": 4.632867813110352, "identity": 0.7289453744888306, "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_Disappointment/48de400e45c461f5897a041672ea7b1cc66652b0fa21a0c5fffb1703df219d5c.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "4909fc71633de8e3d818a567bcff38df5b582ac7833088ce9a87e96ae5e5101a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "679da144219dcd1b0ed287bd004733ea295b5d96d04970be82aad5dd5c8472e1", "generation_seconds_batch": 19.947675686096773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19251397252082825, "target_z": -0.4238281233401045, "ce": 6.292664527893066, "genuineness": 4.444586753845215, "identity": 0.7967246770858765, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4909fc71633de8e3d818a567bcff38df5b582ac7833088ce9a87e96ae5e5101a.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "491d0fc3b728b27e9daf71805bd6fd9250f8227b6162f81e2b2c345af7585aa0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab566034c7f501322e0474534f659a14ba2056a3b7723838211dc25900f550f7", "generation_seconds_batch": 19.09775927697774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30620795488357544, "target_z": -0.261718766598955, "ce": 5.395142555236816, "genuineness": 4.720732688903809, "identity": 0.597559928894043, "hypothesis": "Porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/491d0fc3b728b27e9daf71805bd6fd9250f8227b6162f81e2b2c345af7585aa0.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "49bef9aed0815b05683bafa6188a9dd6c2df721935a30d93770e037097ca1c40", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f3ad1e0ad324da50d43f1046428edbf0f0b1b161eef633e33a850dfe0f666984", "generation_seconds_batch": 19.6200987289194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3473021984100342, "target_z": -0.20312497609750485, "ce": 5.760505676269531, "genuineness": 4.833701133728027, "identity": 0.8358161449432373, "hypothesis": "J'ai trouvé la 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_Disappointment/49bef9aed0815b05683bafa6188a9dd6c2df721935a30d93770e037097ca1c40.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "70ace93103df3e7cac4409e44d114d3a8093c6709b7814b2c59750f137905b65", "generation_seconds_batch": 16.363518350059167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10347649455070496, "target_z": -0.5507812652710385, "ce": 6.1894097328186035, "genuineness": 4.406930446624756, "identity": 0.5342679023742676, "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_Disappointment/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.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": "49f0fa70159bf42895d22f9eda4b1460706bd586269eb1144088de5026c5b995", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4cd34998b9d544b4186fdc0c814196a4148ac6f1e31eb22c262aaaf93a4b6fa6", "generation_seconds_batch": 14.51111136795953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24593645334243774, "target_z": -0.347656246680209, "ce": 5.998785495758057, "genuineness": 4.6203155517578125, "identity": 0.49856036901474, "hypothesis": "Someone moved the little blue chair. It used to s stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/49f0fa70159bf42895d22f9eda4b1460706bd586269eb1144088de5026c5b995.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "4b376f00c53c61c8298eaefcd0bee808da3be859c38eacd1dcc5fed30bac6808", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0fa50857e4c8c2eb5acc37a8b11cf346bb74e10e99f8d348fef4988ea9b47570", "generation_seconds_batch": 19.776369470986538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22127991914749146, "target_z": -0.3828125039837492, "ce": 6.332377910614014, "genuineness": 4.457139015197754, "identity": 0.0926518514752388, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4b376f00c53c61c8298eaefcd0bee808da3be859c38eacd1dcc5fed30bac6808.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "4b38785c7b916163cea7c3b1546d74e676120a6acad1d162629d8b6111f2fe5b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "afa2667369a7fd7e235edb1c23a924e63e3318b044406ff505dcc36ae3599135", "generation_seconds_batch": 21.021900134976022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07608035206794739, "target_z": -0.5898437639431222, "ce": 6.340320587158203, "genuineness": 4.6203155517578125, "identity": 0.4001486897468567, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4b38785c7b916163cea7c3b1546d74e676120a6acad1d162629d8b6111f2fe5b.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "4c396e7c778307c25eb18945f8dd3a86325be884228ff769e8de79134a7045ac", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "eb235941f312b156d999ce76994bab3b95f768831a76bc2b152ec3c708eb4d55", "generation_seconds_batch": 19.306154298014008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3294946849346161, "target_z": -0.2285156299796865, "ce": 5.8875885009765625, "genuineness": 4.494794845581055, "identity": 0.3201468586921692, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4c396e7c778307c25eb18945f8dd3a86325be884228ff769e8de79134a7045ac.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "4c3e7c69fd9da9e882640314e16a45e3e26ffff327100dc59aae519c8b406607", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4205b2c646d7a2f6e8ed3ced07dbf1925aa26f50068f9b217fef48f2969d390", "generation_seconds_batch": 19.445103927049786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35278141498565674, "target_z": -0.195312493360418, "ce": 5.462655067443848, "genuineness": 4.3504462242126465, "identity": 0.5511090755462646, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4c3e7c69fd9da9e882640314e16a45e3e26ffff327100dc59aae519c8b406607.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "4cd99c827f86ae3ece76eff33f9c35aa2b0902c6de929d7051819cdf3f425554", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "920d59bffdf0c1a30c68ea5f0f48a7643fa6bfeb154c2f52ff4410e35e914d73", "generation_seconds_batch": 14.124280603020452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5589373707771301, "target_z": 0.0986327857756825, "ce": 5.7128496170043945, "genuineness": 4.770940780639648, "identity": 0.5663270950317383, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4cd99c827f86ae3ece76eff33f9c35aa2b0902c6de929d7051819cdf3f425554.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "4d14b6769a22598be9f3c87831b4137c8e4f013f37ff8221cdf44d334e80b34a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "db7cccaa2dab47ffcb4a35cfc9b8b78b66afdaa262676a69e1ce4f41e05cb4c4", "generation_seconds_batch": 21.402667595888488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2952495217323303, "target_z": -0.2773437320731286, "ce": 5.824047088623047, "genuineness": 4.833701133728027, "identity": 0.5931944251060486, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4d14b6769a22598be9f3c87831b4137c8e4f013f37ff8221cdf44d334e80b34a.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "4d195e14dc41aaeae29a52dd30af219aee89b111462bb3d0670512edc85b6fa6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "317bd9f035a9a31f50dd99cee5ede7f46a5feca3c645b6aad66edca107485ea1", "generation_seconds_batch": 14.15129143500235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3267550766468048, "target_z": -0.23242187134822992, "ce": 5.959072113037109, "genuineness": 4.934117794036865, "identity": 0.7057508230209351, "hypothesis": "La porte 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_Disappointment/4d195e14dc41aaeae29a52dd30af219aee89b111462bb3d0670512edc85b6fa6.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "4d5bac7eb89d8e79db8bb0107af7a6e263639c53d97d211d10df3e130545bad1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "241febe3c4f79ea2d686e8be59a002306b39bc54f6565034c83b01fa31025e59", "generation_seconds_batch": 19.116041926085018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8294743299484253, "target_z": 0.48437503452582636, "ce": 5.422942161560059, "genuineness": 4.507347106933594, "identity": 0.52915358543396, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4d5bac7eb89d8e79db8bb0107af7a6e263639c53d97d211d10df3e130545bad1.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "4de77425737a2708b4143c67cb73f03ca3fbd13ffbc5b8f1db1af75312038260", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "86d1ebe208b0fb354275313b4258402f1797056f75fde567b020a25a69dafa75", "generation_seconds_batch": 15.737292825011536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2651137709617615, "target_z": -0.32031247211375563, "ce": 6.0305562019348145, "genuineness": 4.432034492492676, "identity": 0.6415994167327881, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4de77425737a2708b4143c67cb73f03ca3fbd13ffbc5b8f1db1af75312038260.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "4e0fcd9525695880f38bff1194cc3f7e026ee6d2184fbd7c993542c34bf3f768", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "55a4dd98da3c98959c650b4209fdca4780644973db1446e651bc67d23d1934d4", "generation_seconds_batch": 19.302563984063454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1363110542297363, "target_z": 0.9218749176691834, "ce": 6.141753673553467, "genuineness": 4.607763767242432, "identity": 0.791073739528656, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4e0fcd9525695880f38bff1194cc3f7e026ee6d2184fbd7c993542c34bf3f768.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "4e18c58fc9b435fbba000633570824e23dc2963c9417b2182c71179f0b1bac4b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4674c465c7f69dfd7a918f636efa5b7bfdd0f0a171cd46dddbd4de3f370ea367", "generation_seconds_batch": 19.786270234035328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10347649455070496, "target_z": -0.5507812652710385, "ce": 5.919358730316162, "genuineness": 4.243753433227539, "identity": 0.8301993608474731, "hypothesis": "J'ai trouvé la 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_Disappointment/4e18c58fc9b435fbba000633570824e23dc2963c9417b2182c71179f0b1bac4b.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "4e9de1d67efb106ccc7087252142d8896358006d50563ec0ac7b9fde9ed9c892", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "42cc0c5f7ef7b47e72ed0910413d187b3c4ad08cc42b74aade66390460f3d3a9", "generation_seconds_batch": 18.965111422003247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8568704128265381, "target_z": 0.5234374482112605, "ce": 5.597680568695068, "genuineness": 4.6705241203308105, "identity": 0.6936699151992798, "hypothesis": "J'ai trouvé la 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_Disappointment/4e9de1d67efb106ccc7087252142d8896358006d50563ec0ac7b9fde9ed9c892.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": "4fc711b56931f54602bd50d52f5049efc60fb7487983666365e61bb56cd7e31b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bcbb2a7434ffebbd4209b10036c4e4af69abd6930923df386dd3fecfe9c74144", "generation_seconds_batch": 19.678380422992632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18977436423301697, "target_z": -0.4277343647086479, "ce": 5.728734970092773, "genuineness": 4.268857479095459, "identity": 0.4607614278793335, "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_Disappointment/4fc711b56931f54602bd50d52f5049efc60fb7487983666365e61bb56cd7e31b.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "4fdf71fbd6d3f45e853211c65bcc08afa2258e8e4891614c327f90ea2804831f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4c372b0a0dcb9d48c42a4955d92973bf0c3f46fab097b09514ef021b7b0ad9b9", "generation_seconds_batch": 22.10424926993437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6705766916275024, "target_z": 0.25781252523041154, "ce": 5.696964263916016, "genuineness": 4.6956281661987305, "identity": 0.7023367881774902, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/4fdf71fbd6d3f45e853211c65bcc08afa2258e8e4891614c327f90ea2804831f.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": "4fffe6e99a7305958a131bb32a1e2546419cd238b2bb4aa3950cfeb4f503b56a", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "006330fbd85ce964016aac764b34653443b2cf7abb8de7b5429971d6ee09fe1b", "generation_seconds_batch": 19.30552566901315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3411380648612976, "target_z": -0.21191404042338988, "ce": 5.287916660308838, "genuineness": 4.13078498840332, "identity": 0.6028232574462891, "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_Disappointment/4fffe6e99a7305958a131bb32a1e2546419cd238b2bb4aa3950cfeb4f503b56a.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "504373feb3fa4fa11a729879b7844168f7f131b9299bc1989d4261426b44780d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d38a537816f04b20f77e2df3e692c372456ec5646f0ad990bc2be040130de0ec", "generation_seconds_batch": 19.446914789034054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08155959844589233, "target_z": -0.5820312387127107, "ce": 5.792276382446289, "genuineness": 4.519899368286133, "identity": 0.3623090088367462, "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_Disappointment/504373feb3fa4fa11a729879b7844168f7f131b9299bc1989d4261426b44780d.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "506b7837f6309b7dbd10625b84963d7347a88581be448476535555c3492db2e5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c2cbc095adc31f977b197b3e967daffdeea471d236358594a0a927de57706c42", "generation_seconds_batch": 18.981963685015216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3651096820831299, "target_z": -0.17773436470864792, "ce": 5.601652145385742, "genuineness": 4.532451152801514, "identity": 0.5363731384277344, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/506b7837f6309b7dbd10625b84963d7347a88581be448476535555c3492db2e5.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "50ab8cb6ef4add981da3545e9179d131c8f390bd3e416be8daf3c011480b44c1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0d130549eab7689eaf96490b258ac823f9da723aa36e46503c4a1078f804d71b", "generation_seconds_batch": 19.445103927049786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47743386030197144, "target_z": -0.017578128651770095, "ce": 5.665193557739258, "genuineness": 4.494794845581055, "identity": 0.5920287370681763, "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_Disappointment/50ab8cb6ef4add981da3545e9179d131c8f390bd3e416be8daf3c011480b44c1.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": "50d8fa63e361968636833cb9eccbf827f4b6c4d08df1cf8d5908bb46c9d30f39", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90cae505fe983e26c5fc9e3d7c3011483ca88e9404ad393769e0b3ff5e6ad146", "generation_seconds_batch": 15.224510548985563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7445462942123413, "target_z": 0.36328129714103213, "ce": 6.125868320465088, "genuineness": 4.6705241203308105, "identity": 0.5083237886428833, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier, naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/50d8fa63e361968636833cb9eccbf827f4b6c4d08df1cf8d5908bb46c9d30f39.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "51405f1e9e5df6b1904b666112c8c279b8e2644ee17d63f70cfb0b59b24f3d2e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "374d5ebfb7bf7689562b475d56832b5dc3f5f1b6a2a0daa1ea74630847876dac", "generation_seconds_batch": 19.280703464057297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6048259139060974, "target_z": 0.16406247742542124, "ce": 6.173524379730225, "genuineness": 4.582659721374512, "identity": 0.7637604475021362, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/51405f1e9e5df6b1904b666112c8c279b8e2644ee17d63f70cfb0b59b24f3d2e.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "516c61231e71d742bd3ff778168fc6d2a570e60a93eaf4d3d02bf1b209b57515", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f4161004bbf1f7314dc4138b48fd54eebd5779fc39c6d6ad932ea3a4ef45dbc9", "generation_seconds_batch": 19.35393814300187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 6.078212261199951, "genuineness": 4.65797233581543, "identity": 0.7597178220748901, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/516c61231e71d742bd3ff778168fc6d2a570e60a93eaf4d3d02bf1b209b57515.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": "5183d3e0c8482ef9cc7957306858be24768b483de2c77ada0443fa6cd98c356b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4612b4ef4149dae1d84d806c53091db0d4a64ba33e67249a52787a784d4b56a6", "generation_seconds_batch": 19.181008634041063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3020985424518585, "target_z": -0.2675781286517701, "ce": 5.450741291046143, "genuineness": 4.482243061065674, "identity": 0.7811706066131592, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Brans-les quand tu partiras.", "wer": 0.041666666666666664, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5183d3e0c8482ef9cc7957306858be24768b483de2c77ada0443fa6cd98c356b.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "523320ad94587c6405f9a41580a197ff8e9c758cbd72f082930e142cdbc54d5a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ce7b9662a46ba6ff9c66378674b7ce21022b22a8859a3a18d198a2537596d6cf", "generation_seconds_batch": 19.448294593021274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3089475631713867, "target_z": -0.25781252523041154, "ce": 5.9431867599487305, "genuineness": 4.356721878051758, "identity": 0.6652419567108154, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/523320ad94587c6405f9a41580a197ff8e9c758cbd72f082930e142cdbc54d5a.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "5233d9c848437bed8214ac2f93541cd1d7cd045123c8d7c379728661e65f8e9f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "99ebb4cd36dcf7b23b8ea83615a78e388ea5af527267f18a561f23b92304ad58", "generation_seconds_batch": 19.02740048104897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0431642532348633, "target_z": 0.7890625411654083, "ce": 5.863759994506836, "genuineness": 4.369274139404297, "identity": 0.5095030069351196, "hypothesis": "Ik 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_Disappointment/5233d9c848437bed8214ac2f93541cd1d7cd045123c8d7c379728661e65f8e9f.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "524a3b9c91bc99a14bead3996f95f7548f69efcaa2ce9a463139bfacba50d565", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba2609429f8addec9aff4c7edd8dd9cb5e1cde6fe4b21940c45134478e1c366d", "generation_seconds_batch": 22.086988972965628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22127991914749146, "target_z": -0.3828125039837492, "ce": 5.824047088623047, "genuineness": 4.7834930419921875, "identity": 0.7357944250106812, "hypothesis": "La porte 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_Disappointment/524a3b9c91bc99a14bead3996f95f7548f69efcaa2ce9a463139bfacba50d565.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "535a25278d0f5df367c640e84fd122a725a9ecb4c4b2ebd92acded7b63657a06", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b271d920d54f87d84f3b4a7bbd6d7a657c2049ce19b5880677b2234946d826d7", "generation_seconds_batch": 14.191523195011541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3007287383079529, "target_z": -0.2695312493360418, "ce": 6.125868320465088, "genuineness": 4.68307638168335, "identity": 0.6377597451210022, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/535a25278d0f5df367c640e84fd122a725a9ecb4c4b2ebd92acded7b63657a06.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "5361768a023721661302f6e1eeac178114011c11a06cce28b47e6beb7ef716e9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8c48121472f1cb7e39639914f2293e83d068f105f8b9a6db08b74a3f89ace248", "generation_seconds_batch": 19.993047722964548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3623700737953186, "target_z": -0.18164060607719135, "ce": 6.141753673553467, "genuineness": 4.607763767242432, "identity": 0.6789859533309937, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5361768a023721661302f6e1eeac178114011c11a06cce28b47e6beb7ef716e9.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": "5374fd9f484bb49fe952bff86bd5500d73dd0c408926a19f0b31c2207760b7b2", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "7f19a045f4e4e2c4c07036c1abf4301d95001628e78ec00df4bb23ac099e925a", "generation_seconds_batch": 19.610477454029024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2158007025718689, "target_z": -0.390624986720836, "ce": 5.847874641418457, "genuineness": 4.65797233581543, "identity": 0.6608574986457825, "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": 0.120000000000001, "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_Disappointment/5374fd9f484bb49fe952bff86bd5500d73dd0c408926a19f0b31c2207760b7b2.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "544764047e8420a1ffa390598008f70345dd7215ad9db6727ceb9ac9094e3932", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "523e71245954e3e73aa9ac7a62c48a7cf24132f485097cd3d28ebc608e763175", "generation_seconds_batch": 19.02740048104897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6014013886451721, "target_z": 0.1591796544680796, "ce": 5.80021858215332, "genuineness": 4.507347106933594, "identity": 0.4972183406352997, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/544764047e8420a1ffa390598008f70345dd7215ad9db6727ceb9ac9094e3932.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "3ac8d9ab84673d4f635555a2d41d18a6ea8e454da0b8139e9932a6523124b549", "generation_seconds_batch": 14.686014799051918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.062382280826568604, "target_z": -0.609375013279164, "ce": 6.24500846862793, "genuineness": 3.848362922668457, "identity": 0.5910427570343018, "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_Disappointment/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "54a51a4d24b58bd2018f27e5dc7c15d34464aa61b1edd1f441c7a1b71a3a9616", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6da7b9dda1e7ac3c2216c232bdd3f9b8824cd1483c09c7493c441a53234d7306", "generation_seconds_batch": 20.11246056202799, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22127991914749146, "target_z": -0.3828125039837492, "ce": 6.086154937744141, "genuineness": 4.494794845581055, "identity": 0.8228044509887695, "hypothesis": "La porte 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_Disappointment/54a51a4d24b58bd2018f27e5dc7c15d34464aa61b1edd1f441c7a1b71a3a9616.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "54a95cc89d213a723d9bc369063c5fedf68f905b0f04c0c485c308ba565d92f5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "418be953adbdd7580b698a3df1a00603555e94190cf094243f57dca2fcca3948", "generation_seconds_batch": 18.981963685015216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5075696110725403, "target_z": 0.025390611388856923, "ce": 5.1052350997924805, "genuineness": 4.432034492492676, "identity": 0.6025645136833191, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/54a95cc89d213a723d9bc369063c5fedf68f905b0f04c0c485c308ba565d92f5.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": "5521d488b9ea0f2eae49a46d57bfdae8c77ef91e94fd59c00bf40763f9e1c3d4", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4a8e1bb39a032d4ef1f7610930f89659fc1520b6a04bc8f5e3ef52dd7dd06013", "generation_seconds_batch": 15.654443441075273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39798504114151, "target_z": -0.1308593832994775, "ce": 5.935244083404541, "genuineness": 4.325342178344727, "identity": 0.48243704438209534, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5521d488b9ea0f2eae49a46d57bfdae8c77ef91e94fd59c00bf40763f9e1c3d4.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": "5523a225f1e6a80b2f1d4f671ba95d266f4303b87fd67a83e35547dfc57c78b9", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f78ac875c2b68d90997f2a99fdc06cd3bbfc7f91b1a40075a170a1fa0bafa02", "generation_seconds_batch": 15.634378265938722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30620795488357544, "target_z": -0.261718766598955, "ce": 5.736677646636963, "genuineness": 4.268857479095459, "identity": 0.4000585079193115, "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_Disappointment/5523a225f1e6a80b2f1d4f671ba95d266f4303b87fd67a83e35547dfc57c78b9.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "55337f5969bc9822ce15eb059c380f13632689fe786f1371cb97d8e85b179a2d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8b9b28f082d98110f1188bcea47ebccd8276c4304b5169c8af57574e8a8cad7c", "generation_seconds_batch": 20.622409850009717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35278141498565674, "target_z": -0.195312493360418, "ce": 5.8875885009765625, "genuineness": 4.632867813110352, "identity": 0.744706392288208, "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_Disappointment/55337f5969bc9822ce15eb059c380f13632689fe786f1371cb97d8e85b179a2d.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "555a3fefe285dae56732de37576de8f3e7b8d4c5620fff14772480188783af02", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a69c14b30e576315e2fb4cf06dedea3c86996e55d6946cb259a6b802208e56b0", "generation_seconds_batch": 19.81411392998416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1336122751235962, "target_z": -0.5078124827370868, "ce": 5.911416053771973, "genuineness": 4.770940780639648, "identity": 0.736359715461731, "hypothesis": "J'ai trouvé la 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_Disappointment/555a3fefe285dae56732de37576de8f3e7b8d4c5620fff14772480188783af02.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "558f530999b538bced535ddcb50733f3bbff1c137a5fe9e9d6ded8cc5e88f348", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c0201ef429950be01a395a4544badd9a91f23be3bcec2e49ccd2eb31d386deff", "generation_seconds_batch": 14.69353727903217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5664713382720947, "target_z": 0.10937501327916398, "ce": 6.181467056274414, "genuineness": 4.369274139404297, "identity": 0.6796576976776123, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/558f530999b538bced535ddcb50733f3bbff1c137a5fe9e9d6ded8cc5e88f348.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "55f0b16f16eac56d7d1b0a6fa581e956ba252c9b334f73c95a9e102724bdc622", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "869d609bf689bdc8f1ee7fcbcf04faaae168f717b42f0ed05f8b9656a1d51f85", "generation_seconds_batch": 22.704326160019264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22812896966934204, "target_z": -0.37304685806906596, "ce": 6.205295085906982, "genuineness": 4.507347106933594, "identity": 0.5721253156661987, "hypothesis": "The 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_Disappointment/55f0b16f16eac56d7d1b0a6fa581e956ba252c9b334f73c95a9e102724bdc622.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "561aaa1fa3146d53383cf7874464a1a6447f12fdc23ae51520d8bf3a9687a758", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3786f33787eb21105a65f69445320c981b1bc9d2f615ffbe24eef39ffff1d32f", "generation_seconds_batch": 20.881567530101165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22401952743530273, "target_z": -0.37890626261520577, "ce": 6.0305562019348145, "genuineness": 4.607763767242432, "identity": 0.4718528985977173, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/561aaa1fa3146d53383cf7874464a1a6447f12fdc23ae51520d8bf3a9687a758.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "566af1fe9c5d5947f0ecfb95ff22d2be0de3f16f7e9b829e59ac820ad39e1adb", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "17d4e1e211b175db8b8bed2bc6bf97e82192c3a79dd76c04d1a1fcd2b2749d55", "generation_seconds_batch": 15.901431978098117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16374802589416504, "target_z": -0.46484374269645984, "ce": 6.078212261199951, "genuineness": 4.457139015197754, "identity": 0.6206886768341064, "hypothesis": "La porte 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_Disappointment/566af1fe9c5d5947f0ecfb95ff22d2be0de3f16f7e9b829e59ac820ad39e1adb.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "5677ef24974c8fc2c2c2c316f83e7c48b6e92cc92708b6f7f48ede6f7d00893d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a6b0944ea9f7a9a9b1f76f7edadafa5126a6d90dc34b124d5c3db3bfdd9ef688", "generation_seconds_batch": 19.35028323403094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1336122751235962, "target_z": -0.5078124827370868, "ce": 6.348263263702393, "genuineness": 4.607763767242432, "identity": 0.4597175121307373, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5677ef24974c8fc2c2c2c316f83e7c48b6e92cc92708b6f7f48ede6f7d00893d.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "570601126cfd6d3bd05883ae0375f4e27914357bc573a142eb3cb63551f60636", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dfc9eecb333ee563441e019347b869561d75453f26f7fa764296248d0d8acfea", "generation_seconds_batch": 14.043995323008858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.291140079498291, "target_z": -0.2832031366192685, "ce": 5.7406487464904785, "genuineness": 4.432034492492676, "identity": 0.44199949502944946, "hypothesis": "The 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_Disappointment/570601126cfd6d3bd05883ae0375f4e27914357bc573a142eb3cb63551f60636.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "57c1b6db57aeb88690a7a814637e5312039b914191d89a6ce648124e5e8448b8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "469b25a17f434e8f6ca5e55172a902cf3db48a8b32623b7ff577dfb43f61e204", "generation_seconds_batch": 14.106301838997751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3514115810394287, "target_z": -0.19726565653801445, "ce": 5.863759994506836, "genuineness": 4.821148872375488, "identity": 0.625826358795166, "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_Disappointment/57c1b6db57aeb88690a7a814637e5312039b914191d89a6ce648124e5e8448b8.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "57f121307c3d8e04c3fb7aae63a9463075413b419f22c9f3096f44fb24f7d8a8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb6dc86629070b0d97417e25c0c456f64eab30ce48e892e692a57c9f19e60968", "generation_seconds_batch": 14.197549600969069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10621613264083862, "target_z": -0.5468749814091705, "ce": 6.070269584655762, "genuineness": 4.65797233581543, "identity": 0.6361786723136902, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/57f121307c3d8e04c3fb7aae63a9463075413b419f22c9f3096f44fb24f7d8a8.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "5877258cf8e43bf5878e3354df56bdce7f5ebba148062dc5a5a57f7cf30edf87", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f37bf84b7b557137e281bb840b63bdf5a3a771f62c4e4d81e890d81d0627df5c", "generation_seconds_batch": 23.968709630076773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.051423847675323486, "target_z": -0.6249999787533377, "ce": 6.372091293334961, "genuineness": 4.68307638168335, "identity": 0.4252065420150757, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5877258cf8e43bf5878e3354df56bdce7f5ebba148062dc5a5a57f7cf30edf87.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "58adbbe36edd0f5083b19e2001d7f94accfb3246fb5bdef146024615023d25d2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "974cec4aaedce3a066c68e14688170488526784035313022ce9926dce80f3121", "generation_seconds_batch": 15.560155040002428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5027753114700317, "target_z": 0.01855471024056831, "ce": 6.125868320465088, "genuineness": 4.532451152801514, "identity": 0.7573894262313843, "hypothesis": "De deur 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_Disappointment/58adbbe36edd0f5083b19e2001d7f94accfb3246fb5bdef146024615023d25d2.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "58b3e94c507bf5172497f68fb81463179ba589aa7b833de84b87f8b82d0005d7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "42494219727119cbb686357fd0b6943a42cd86d1478da8954538ea2b8ff93a07", "generation_seconds_batch": 15.352958665927872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07060113549232483, "target_z": -0.597656246680209, "ce": 6.356205940246582, "genuineness": 4.770940780639648, "identity": 0.3989090919494629, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/58b3e94c507bf5172497f68fb81463179ba589aa7b833de84b87f8b82d0005d7.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "58d37b6b442dc71121b9ee389ef06420908425c454534fd1354dcf662865d98e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9bc129ca1a21862aa303f3fc8448d42398c2d5d37eae23ee79b03626375d6488", "generation_seconds_batch": 14.159526592935435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3377135396003723, "target_z": -0.2167968633807315, "ce": 5.689021587371826, "genuineness": 4.632867813110352, "identity": 0.5199662446975708, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/58d37b6b442dc71121b9ee389ef06420908425c454534fd1354dcf662865d98e.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "58e68ee6ad95da90e727fa191cf7cc706c6192cef63858ebc7ab60f1bda274f5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f4a5dbb6d9b3073f36aa32386ff791f8350b45ed74ad078372a417fd36a83572", "generation_seconds_batch": 19.6200987289194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18292531371116638, "target_z": -0.43750001062333116, "ce": 5.597680568695068, "genuineness": 4.65797233581543, "identity": 0.8096747994422913, "hypothesis": "J'ai trouvé la 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_Disappointment/58e68ee6ad95da90e727fa191cf7cc706c6192cef63858ebc7ab60f1bda274f5.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "58ea845845bba3ffbcfc57f4c237a67f321a7a672059682b22568ae75a54d0a1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6541c07b0a0edc452fd3938c68731169ca333e5ae4f9804769eef16d70f0304d", "generation_seconds_batch": 15.64164120098576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.419901967048645, "target_z": -0.09960936736448071, "ce": 5.792276382446289, "genuineness": 4.65797233581543, "identity": 0.7698074579238892, "hypothesis": "J'ai trouvé la 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_Disappointment/58ea845845bba3ffbcfc57f4c237a67f321a7a672059682b22568ae75a54d0a1.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "596f46e6c9ffe5c0cc69e54f0e61855e070f859f497b5e1cb50a5006931ec817", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2bd2aca012e5e2a66073dc9d8ecf7ac9f22a4cc5e8acbbaf98bd015a01522a95", "generation_seconds_batch": 16.607004103949293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.291140079498291, "target_z": -0.2832031366192685, "ce": 5.824047088623047, "genuineness": 4.645420074462891, "identity": 0.48030221462249756, "hypothesis": "la puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/596f46e6c9ffe5c0cc69e54f0e61855e070f859f497b5e1cb50a5006931ec817.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "59790c371ad297b4bc2b7501637bf836152074fef5fd76e638cd166edaa51a6e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5f4663ff46c0529fe201aa30e68f6cc638283b877efcdfcea86d9859acbe413c", "generation_seconds_batch": 20.30152127891779, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08429920673370361, "target_z": -0.5781249973441672, "ce": 6.173524379730225, "genuineness": 4.519899368286133, "identity": 0.6788493394851685, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/59790c371ad297b4bc2b7501637bf836152074fef5fd76e638cd166edaa51a6e.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "59f5438788d08dbb14234cfb268f9b8e8c218267180ad5105387a7f5682abdd3", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e3568431f9e29a140bb3069bae6a126d315eac7785f93fd029d45f7f18e7a6e", "generation_seconds_batch": 19.196477279998362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7527651190757751, "target_z": 0.3750000212466624, "ce": 5.375286102294922, "genuineness": 4.293961524963379, "identity": 0.40741628408432007, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/59f5438788d08dbb14234cfb268f9b8e8c218267180ad5105387a7f5682abdd3.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "5a32bac4e1623cc22b9a97bc5e5d49151aa32b5f55f9fe7adaffc378e467f8c2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a83d434b399e743eaa664ebcee2a32b699876932ae6d8c6c77ea925cad543af0", "generation_seconds_batch": 22.10424926993437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5534581542015076, "target_z": 0.09082030303859567, "ce": 5.816103935241699, "genuineness": 4.582659721374512, "identity": 0.8173257112503052, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5a32bac4e1623cc22b9a97bc5e5d49151aa32b5f55f9fe7adaffc378e467f8c2.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "5a69739e57b0f483528406c8662b28e1c20bd76d730a05f5cb9df8b414851fa2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e769ca3c5b69277b370ea3f9ddfe78ff03737b71039f943cf78d977825bee32", "generation_seconds_batch": 16.113613507011905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7883800864219666, "target_z": 0.4257812440243762, "ce": 5.879645347595215, "genuineness": 4.143336772918701, "identity": 0.32516998052597046, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5a69739e57b0f483528406c8662b28e1c20bd76d730a05f5cb9df8b414851fa2.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "5ab271bed560cf11c1acb8ec830515d09795ecd1723a49c49b25a8cc01f9ab25", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1fdbcdee6ed398b7aa0249b5d1f32f9496b237890792ef143e2361a2a4b67026", "generation_seconds_batch": 14.404255851055495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19662338495254517, "target_z": -0.4179687612872894, "ce": 5.609594821929932, "genuineness": 4.507347106933594, "identity": 0.634605348110199, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5ab271bed560cf11c1acb8ec830515d09795ecd1723a49c49b25a8cc01f9ab25.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "5ac0ca8047cd27d9bc335cf22abce8759f26140edd3de8aeba303483e036d92b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d1b4e5b2203423da90487c8ed16c2612ae3f31c8c55acd17a541067c3c09353f", "generation_seconds_batch": 14.301091230940074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6801652908325195, "target_z": 0.2714843275269888, "ce": 5.788304805755615, "genuineness": 4.3881025314331055, "identity": 0.6442917585372925, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5ac0ca8047cd27d9bc335cf22abce8759f26140edd3de8aeba303483e036d92b.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "5b19f90d9c40f7d28dc00b667624d4f4ded777838e407d8dc8d33c6086236e94", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "23370a3a18bb903faf1bc598ddea7f75babdb9683e78eda107b44e5046351f00", "generation_seconds_batch": 22.48388595005963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11443495750427246, "target_z": -0.5351562573035402, "ce": 6.022613525390625, "genuineness": 4.13078498840332, "identity": 0.5729268193244934, "hypothesis": "The 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_Disappointment/5b19f90d9c40f7d28dc00b667624d4f4ded777838e407d8dc8d33c6086236e94.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "5b93908dcac1a45e9f8f28e6803e00b583431187cd82052759ff87bf29b9ddce", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ee9f30662086e3fde0656882b5ac96c90df9709d3fd23a8cb663c9582995e678", "generation_seconds_batch": 19.088805068051443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5808542966842651, "target_z": 0.12988280171067926, "ce": 5.816103935241699, "genuineness": 4.808597087860107, "identity": 0.7078992128372192, "hypothesis": "La puerta sigue abierta. he dejado tu ahrigo 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_Disappointment/5b93908dcac1a45e9f8f28e6803e00b583431187cd82052759ff87bf29b9ddce.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "5bd338c9bbc0019f3ab8e302a60eaa82c484ebd706f911a2749560c1d1d5b94f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d96d02a6d5ad17bd0849c3141b22b6307c0cde107e694de7f3f8ea7f124f6f01", "generation_seconds_batch": 19.139526894898154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.291140079498291, "target_z": -0.2832031366192685, "ce": 5.307773113250732, "genuineness": 4.331617832183838, "identity": 0.41126418113708496, "hypothesis": "The 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_Disappointment/5bd338c9bbc0019f3ab8e302a60eaa82c484ebd706f911a2749560c1d1d5b94f.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "5c17de29c8ba0f4dba1805f5ac0c5e6ee4ba777c025e08ea32943b69b8e359d3", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b37df02bc970fd20a3942a1191f13c9b9c23e84a03e30cd0c4eaded70dd20a13", "generation_seconds_batch": 20.399821860948578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17607629299163818, "target_z": -0.44726561404468973, "ce": 6.324435234069824, "genuineness": 4.632867813110352, "identity": 0.5428180694580078, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5c17de29c8ba0f4dba1805f5ac0c5e6ee4ba777c025e08ea32943b69b8e359d3.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "5c8d756d9121c2a0110fd5cf677de2946f767c43459d63c4fee1d7a1c456eb94", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1ad546d006b6b0136eb1dd3c7fbd913dbeb74949b8a506b9a29ab40242b3e510", "generation_seconds_batch": 19.317675288999453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6089353561401367, "target_z": 0.16992188197156108, "ce": 5.824047088623047, "genuineness": 4.457139015197754, "identity": 0.48679399490356445, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5c8d756d9121c2a0110fd5cf677de2946f767c43459d63c4fee1d7a1c456eb94.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "917fdd611bd709f141a942d88e588c4cea0974469ffcd5c09c939fcd47d7e029", "generation_seconds_batch": 14.479995705070905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19662338495254517, "target_z": -0.4179687612872894, "ce": 6.197352409362793, "genuineness": 4.268857479095459, "identity": 0.7595977783203125, "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_Disappointment/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "5e1e70a908d7aa86125a516c7df5f509518448a68c1f55e1f8151ac73f5766a5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6910c1319174c441adfb1732ad774765c159ac0dde2c336ecb2b647fbf993ef0", "generation_seconds_batch": 14.49425812496338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24593645334243774, "target_z": -0.347656246680209, "ce": 5.871703147888184, "genuineness": 4.557555198669434, "identity": 0.5067526698112488, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5e1e70a908d7aa86125a516c7df5f509518448a68c1f55e1f8151ac73f5766a5.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "5e488b21139231cc7edd262a47f9508cade10eb5d823a726768a01eaa2e5123e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "417face7ff1c681d9a57d45b57529692f065975446d7c47ddc7194bd77016f1a", "generation_seconds_batch": 19.424026191001758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.419901967048645, "target_z": -0.09960936736448071, "ce": 5.911416053771973, "genuineness": 4.532451152801514, "identity": 0.6139660477638245, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5e488b21139231cc7edd262a47f9508cade10eb5d823a726768a01eaa2e5123e.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": "5f975e437e2c8e329dd3f89c204d3b9ffb4ef91f572355181b0230752eb4faba", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f28b51a9409e08e574aa834ee849bd83c2e80ccb3937e69bc277ffa84639e184", "generation_seconds_batch": 19.45972715993412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3007287383079529, "target_z": -0.2695312493360418, "ce": 6.070269584655762, "genuineness": 4.557555198669434, "identity": 0.37915217876434326, "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_Disappointment/5f975e437e2c8e329dd3f89c204d3b9ffb4ef91f572355181b0230752eb4faba.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "5fe4fcc2cafb6a939ad6a92f1688e2d00733c787e1a9ee67bcde5fedac59671c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "08ab6864b213a86ea53c3913d8c51a6fdc944639f6fc91b36065741bb7d5e5e1", "generation_seconds_batch": 19.24692635401152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17196685075759888, "target_z": -0.45312501859082954, "ce": 5.919358730316162, "genuineness": 4.796044826507568, "identity": 0.7400129437446594, "hypothesis": "J'ai trouvé la 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_Disappointment/5fe4fcc2cafb6a939ad6a92f1688e2d00733c787e1a9ee67bcde5fedac59671c.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": "5fecc8efeb3a928a2126f1220977f355ae58bcf87c091937cf25de9043da73d6", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2c9a36d67cf65a53a83b9b39c9c0b999da7c2c40b1e23184583ee71f418de8ef", "generation_seconds_batch": 15.125061876955442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3829171657562256, "target_z": -0.152343753319791, "ce": 5.609594821929932, "genuineness": 4.356721878051758, "identity": 0.09396598488092422, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/5fecc8efeb3a928a2126f1220977f355ae58bcf87c091937cf25de9043da73d6.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": "5ff1f3e933a59e2108a0a69d6e8441e145bd6cae4e632c183d41d5056ba7adda", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f693c7728674fd558862e580537f045056ce22e8e822d6411ba16cad93f7b05b", "generation_seconds_batch": 19.45972715993412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21717050671577454, "target_z": -0.38867186603656434, "ce": 5.744620323181152, "genuineness": 4.432034492492676, "identity": 0.26511865854263306, "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_Disappointment/5ff1f3e933a59e2108a0a69d6e8441e145bd6cae4e632c183d41d5056ba7adda.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "60eac26708d2713c8b71a64f5b19f128d10fcf0fe63a0e07b9527d05e878faef", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2748baa3f90fc6074d69eb2b997d975c9b33ef70ba7d1e43411542457cd93edb", "generation_seconds_batch": 18.959899227018468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9363192319869995, "target_z": 0.6367187028589679, "ce": 5.3514580726623535, "genuineness": 3.9676074981689453, "identity": 0.3745400309562683, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/60eac26708d2713c8b71a64f5b19f128d10fcf0fe63a0e07b9527d05e878faef.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "6166df2aa5a908bc4aea34a4185d40b4189557b924525322439572b1a473138e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "87a39360c3b3fb35bf099be04feb5da5fe844a0629784890cad69ceb5ef0a375", "generation_seconds_batch": 19.95152410492301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09525766968727112, "target_z": -0.5624999893766688, "ce": 6.046441555023193, "genuineness": 4.65797233581543, "identity": 0.7111445665359497, "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_Disappointment/6166df2aa5a908bc4aea34a4185d40b4189557b924525322439572b1a473138e.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": "61c68c1bd8642290842d864cb45b848a8629c1ceb506b14bef2b725d1745c0e5", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0321b02907cb5785969f44c8e26ba75d2543c1ccbee7464869585fd82feeef64", "generation_seconds_batch": 15.138412976055406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.240457221865654, "target_z": -0.3554687506639582, "ce": 5.974957466125488, "genuineness": 4.821148872375488, "identity": 0.7408058643341064, "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_Disappointment/61c68c1bd8642290842d864cb45b848a8629c1ceb506b14bef2b725d1745c0e5.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "623ec3cf111ed36ef2bf39ab3e17378af523dbe11b25bb671506538b66c0aca9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2580beb8ace21716ee114d909a02c5c46d9a3addd8505ab28fde1b31ec500acf", "generation_seconds_batch": 19.133516883011907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.034986138343811035, "target_z": -0.6484375119512475, "ce": 6.149696350097656, "genuineness": 4.607763767242432, "identity": 0.47397470474243164, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/623ec3cf111ed36ef2bf39ab3e17378af523dbe11b25bb671506538b66c0aca9.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "6260f8952f650db6c5dcdae2a60afd1bf4581dff6a426f8248d9d5a8260770aa", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7d265c277c19da231044c44883e2aa2d4b04a43b48243572162aef3204fde6fe", "generation_seconds_batch": 21.60452004696708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28155142068862915, "target_z": -0.29687502390249515, "ce": 6.1020402908325195, "genuineness": 4.557555198669434, "identity": 0.42885661125183105, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6260f8952f650db6c5dcdae2a60afd1bf4581dff6a426f8248d9d5a8260770aa.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "62a68e62f8252d8751fda824ba547452c9e4d162dd18fde5975d680586815dc2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "77147d1b861fa5e55861fd32eb6d402bd670a62715bd9c99d59264bf5525e547", "generation_seconds_batch": 19.13464008201845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7924895286560059, "target_z": 0.43164064857051604, "ce": 5.847874641418457, "genuineness": 4.7834930419921875, "identity": 0.7525488138198853, "hypothesis": "J'ai trouvé la 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_Disappointment/62a68e62f8252d8751fda824ba547452c9e4d162dd18fde5975d680586815dc2.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "62ed714a5e49aa368090a613a9810b0c7229eef88224acd339a2c387f2010df7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0cd43439676c9bc90a5410ab1e0b1828767f3d177bbe076b1e31ce1a988b44d1", "generation_seconds_batch": 19.076112948008813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1226129531860352, "target_z": 0.9023436258398169, "ce": 5.6413655281066895, "genuineness": 4.356721878051758, "identity": 0.2871630787849426, "hypothesis": "De deur staat nog open. Ik heb je juist op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/62ed714a5e49aa368090a613a9810b0c7229eef88224acd339a2c387f2010df7.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "63197e87f88875327d3455457e2c224b4d1ca23da0f18df2391fdffb3e902305", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "456a617f7578badb1b239195ae21a0b0573eb921452012459b57540cb48a70e6", "generation_seconds_batch": 18.75619635405019, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18566492199897766, "target_z": -0.43359376925478776, "ce": 5.9431867599487305, "genuineness": 4.218649387359619, "identity": 0.40895846486091614, "hypothesis": "The 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_Disappointment/63197e87f88875327d3455457e2c224b4d1ca23da0f18df2391fdffb3e902305.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "6344db631511b589160f918a5dc375bb0fb556330c1320b84680db2a31792755", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7c1cddfbf73b598b64f1fb6f1af0e808045ac9c653242a389a0ce8a407c497a2", "generation_seconds_batch": 19.333276877063327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18155550956726074, "target_z": -0.4394531313076029, "ce": 5.959072113037109, "genuineness": 4.7458367347717285, "identity": 0.7329267263412476, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6344db631511b589160f918a5dc375bb0fb556330c1320b84680db2a31792755.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "635063ac1ad289d15a15fceb96dbd35e2365a693ebde977536513391284984dd", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04ad99d271ead664d475718989321c9f103da2ceed3d8f9ebcad4008a6b4ba64", "generation_seconds_batch": 21.244034571922384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5719505548477173, "target_z": 0.11718749601625081, "ce": 5.998785495758057, "genuineness": 4.6203155517578125, "identity": 0.4886660575866699, "hypothesis": "De... de taart nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/635063ac1ad289d15a15fceb96dbd35e2365a693ebde977536513391284984dd.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": "63941e44ab1b75be8efc771cb8f5bce9fcc3c6f804d8e35fc15ed83fc164dffe", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d0f1de348fea06ff2345a08ea294398f236d028c3639203fd5bc935087c198e", "generation_seconds_batch": 15.537088027922437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32812488079071045, "target_z": -0.2304687506639582, "ce": 6.316492557525635, "genuineness": 4.7458367347717285, "identity": 0.37811481952667236, "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_Disappointment/63941e44ab1b75be8efc771cb8f5bce9fcc3c6f804d8e35fc15ed83fc164dffe.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": "6398801f3225596cb01eefbcb26afae627520e5db8c38eebba5d9c3e017d0d20", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e8e34f94ab088f9f5baab960eb9862769118626042068e5352f1afb95184b9f", "generation_seconds_batch": 19.352830540039577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.377437949180603, "target_z": -0.16015623605687782, "ce": 5.879645347595215, "genuineness": 4.7081804275512695, "identity": 0.6216927766799927, "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_Disappointment/6398801f3225596cb01eefbcb26afae627520e5db8c38eebba5d9c3e017d0d20.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "63b2a175493a6327cd7137c1dd30e1a32a80c165dbb432dcf84cca24804b7090", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fead9a1d86fbaf1c1f23557b028148fc6be88562cb69ed70aeacb1973778a46c", "generation_seconds_batch": 19.046880087000318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5671562552452087, "target_z": 0.11035159486796219, "ce": 6.0305562019348145, "genuineness": 4.432034492492676, "identity": 0.4827420115470886, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. 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_Disappointment/63b2a175493a6327cd7137c1dd30e1a32a80c165dbb432dcf84cca24804b7090.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "63bb8794d2f1b7c6985ea1335fb1c6bd6328dd119faa87595f83a13283d39635", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "86c725469d20fcc6fae4bff3c77cdf0985fb0d576f9cb8b53c4c536526fa6e66", "generation_seconds_batch": 23.32112313003745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4253811836242676, "target_z": -0.09179688462739388, "ce": 5.982900142669678, "genuineness": 4.7081804275512695, "identity": 0.7242401838302612, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/63bb8794d2f1b7c6985ea1335fb1c6bd6328dd119faa87595f83a13283d39635.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": "63e4375d22d613236c289708e27c407121e6e2c9d807264afdc61501f414c0e4", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "53c3d2d746a2ffdcd5a3693df277829d47f8e33bee347bc2e9bc9b422237250d", "generation_seconds_batch": 15.63191532692872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 5.637393951416016, "genuineness": 4.582659721374512, "identity": 0.38822656869888306, "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_Disappointment/63e4375d22d613236c289708e27c407121e6e2c9d807264afdc61501f414c0e4.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "63f3b4d93c451b8a576a1c36cbf942fa5ee80c2f6b3e8bf2a2e52a5bb662d9b0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "40d97895ae65f286a8620b3d62a16039a79033a1bb722f5a22fec3e77b0fe587", "generation_seconds_batch": 20.228206739062443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.056903064250946045, "target_z": -0.6171874960162508, "ce": 6.403861999511719, "genuineness": 4.413206577301025, "identity": 0.40711772441864014, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/63f3b4d93c451b8a576a1c36cbf942fa5ee80c2f6b3e8bf2a2e52a5bb662d9b0.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "6527d92a4d5e25fb4678aedc216252b45f7cf591f72980ce3b5d0cf8023966da", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "873274766191eed6ff3c66e65fa47eae0542ea844a5b12fff819b9fd761537bf", "generation_seconds_batch": 20.37914442399051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1404612958431244, "target_z": -0.4980468793157283, "ce": 6.23706579208374, "genuineness": 4.519899368286133, "identity": 0.7228246927261353, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6527d92a4d5e25fb4678aedc216252b45f7cf591f72980ce3b5d0cf8023966da.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "656adcf48ad21a4988cd973e727cfa85f9035d3073d91015d187e95fd79048e6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2569ea0885858b4d5d0b5f5a60054c094f0468721949ed6cf4975beba5d8f30", "generation_seconds_batch": 19.388031775015406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19662338495254517, "target_z": -0.4179687612872894, "ce": 6.181467056274414, "genuineness": 4.482243061065674, "identity": 0.47994160652160645, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/656adcf48ad21a4988cd973e727cfa85f9035d3073d91015d187e95fd79048e6.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": "65941723c3e0867677c2cc5ba4dc3b94af522fc6b552c968f53067f579ceea19", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "970eb0169d19b4b1784fc60c8137789a5cbc0a3fffa67a19f137fd742ff2eeaf", "generation_seconds_batch": 19.24914996197913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17881590127944946, "target_z": -0.4433593726761463, "ce": 5.609594821929932, "genuineness": 4.545003414154053, "identity": 0.48211050033569336, "hypothesis": "Escribí el número en el sobre, léalo 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_Disappointment/65941723c3e0867677c2cc5ba4dc3b94af522fc6b552c968f53067f579ceea19.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "65a0d1921b3009fb9742885f2c9c72ec87e435af2170df6dac107b317be76b16", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7dd7650bf7099effaab9221314b9d2bd5d89264c1027149c5ed405913c41a757", "generation_seconds_batch": 22.32634184602648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26374393701553345, "target_z": -0.3222656352913521, "ce": 5.77639102935791, "genuineness": 4.7081804275512695, "identity": 0.7044087052345276, "hypothesis": "J'ai trouvé la 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_Disappointment/65a0d1921b3009fb9742885f2c9c72ec87e435af2170df6dac107b317be76b16.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": "661eaf561a0716c9c40d065cb88ff073b33782a36400fdf2eb1df54cdea7326c", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b11c8aa7268280442b6ab9d773e8ac72b2d875101be8973959988de4a47a88ac", "generation_seconds_batch": 14.340960153960623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21032145619392395, "target_z": -0.3984375119512476, "ce": 5.855817794799805, "genuineness": 4.331617832183838, "identity": 0.8273311853408813, "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_Disappointment/661eaf561a0716c9c40d065cb88ff073b33782a36400fdf2eb1df54cdea7326c.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "6665581c8f262f8efc6121598011c939bf8bad5bb303666ef06a3517a6d3fa12", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a215ef5bb63d47d5c7e7e2b50a59fa7a4ba779933e8034acca7b299505f6f002", "generation_seconds_batch": 19.01168607699219, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24319683015346527, "target_z": -0.35156250929541477, "ce": 5.831989288330078, "genuineness": 4.7834930419921875, "identity": 0.7997637391090393, "hypothesis": "La porte 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_Disappointment/6665581c8f262f8efc6121598011c939bf8bad5bb303666ef06a3517a6d3fa12.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "67920345a45246d8b7154804db8117c6ccb8c188177e03ba81b366403bbb31f6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "53957b4ebb459a76d181d7829bf8e235d073872bc9ab79e1accea34bc0ebf35f", "generation_seconds_batch": 19.880609962972812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43907925486564636, "target_z": -0.07226563529135208, "ce": 6.221180438995361, "genuineness": 4.469690799713135, "identity": 0.6979072093963623, "hypothesis": "Ik heb een klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/67920345a45246d8b7154804db8117c6ccb8c188177e03ba81b366403bbb31f6.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": "67cc0b9a121705d55c1ad6b86caeed5e9d4f3e8900e3538d89b839bab6ba0695", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dca44877590097527ec3e05c1ed1d068fe7f21454f9ab7cc5da7168bfe1c52f2", "generation_seconds_batch": 15.24554731999524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8760477304458618, "target_z": 0.5507812227777138, "ce": 5.5659098625183105, "genuineness": 4.7458367347717285, "identity": 0.6495288610458374, "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_Disappointment/67cc0b9a121705d55c1ad6b86caeed5e9d4f3e8900e3538d89b839bab6ba0695.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "67d82d8d2a997e7a654cdd754f23fea7e79540ab171e299aa85d5f415ef3204e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c75636f0bb371d5589918e5cadefb2513d51fa0a1d588ee858dd90b5d80e6aad", "generation_seconds_batch": 14.397154332953505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33086448907852173, "target_z": -0.22656250929541477, "ce": 5.831989288330078, "genuineness": 4.871357440948486, "identity": 0.8221039772033691, "hypothesis": "J'ai trouvé la 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_Disappointment/67d82d8d2a997e7a654cdd754f23fea7e79540ab171e299aa85d5f415ef3204e.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "680b8bb50e8ff26038ff91c578b4ab9c0266a53f7b0a8d54ec353c700c76cf19", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "093be567d3c5d9364ce44df0814355d2fae6d4a1e81c39b82082c2cf08a80f26", "generation_seconds_batch": 14.333551007090136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6390711069107056, "target_z": 0.2128906220121881, "ce": 5.903473377227783, "genuineness": 4.846253395080566, "identity": 0.7966412901878357, "hypothesis": "J'ai trouvé la 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_Disappointment/680b8bb50e8ff26038ff91c578b4ab9c0266a53f7b0a8d54ec353c700c76cf19.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": "681c68062ed1f0991f2da17193b203a18cc5602d50f3e0a744d69d7bbf11acba", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2dd14ef8a252aa18226d8bd5f4cb0d89ca726f77eed3e899304854f1cab38828", "generation_seconds_batch": 14.526228441973217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49661117792129517, "target_z": 0.009765645914683263, "ce": 5.80021858215332, "genuineness": 4.557555198669434, "identity": 0.6721084117889404, "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_Disappointment/681c68062ed1f0991f2da17193b203a18cc5602d50f3e0a744d69d7bbf11acba.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "68294465ee0003d87bb30c84f13c354c856226f141e8e570af56b41a60514d8a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8c8a19cf18519551b0ceb22e921cca4e8c8ff0d74739f046b329bbddbcc681f7", "generation_seconds_batch": 19.604396044043824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2842910587787628, "target_z": -0.292968740040627, "ce": 6.133810997009277, "genuineness": 4.582659721374512, "identity": 0.5358567237854004, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/68294465ee0003d87bb30c84f13c354c856226f141e8e570af56b41a60514d8a.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "6920e0cd97c8798a43b4da14a9cf0d743f38a48bfd5f9ff063a39ed011102e4d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fd49c376d4fcbfec795c2e93da46e55252b0e5a2e56ca8514ed3b1990b46e897", "generation_seconds_batch": 19.60932068096008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5322261452674866, "target_z": 0.06054686869239711, "ce": 6.086154937744141, "genuineness": 4.507347106933594, "identity": 0.5622323751449585, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6920e0cd97c8798a43b4da14a9cf0d743f38a48bfd5f9ff063a39ed011102e4d.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "695e45aea2adb237f3b05ff1197777c367e588a34b1334575e841efc63823378", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "730a11710f341ea96c5c659ebc09f16f6d58f2484e49082f48cae01e735852eb", "generation_seconds_batch": 14.439944087993354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3452474772930145, "target_z": -0.20605467837057476, "ce": 6.24500846862793, "genuineness": 4.394378662109375, "identity": 0.585469126701355, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/695e45aea2adb237f3b05ff1197777c367e588a34b1334575e841efc63823378.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "698569e1e3b6ad4582824a8567ec3eb8ca7ae604772080bbfe2f3503db6541b1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6316248389e23c5a1d6778c5dd4d1a334312473b4f78501c01cca8c32d993c5c", "generation_seconds_batch": 19.050823209923692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20621204376220703, "target_z": -0.4042968740040627, "ce": 5.8875885009765625, "genuineness": 4.595211505889893, "identity": 0.5143744945526123, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/698569e1e3b6ad4582824a8567ec3eb8ca7ae604772080bbfe2f3503db6541b1.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "69d684aff342775ed514679546e5d7f54563e02866688e75c6e9508b544a0cfc", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3129623403562b789958dbd773ed3f713b52ebe1de68d0971a60e8f781ed535c", "generation_seconds_batch": 19.133516883011907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04594460129737854, "target_z": -0.6328125039837492, "ce": 6.395919322967529, "genuineness": 4.720732688903809, "identity": 0.5092458724975586, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/69d684aff342775ed514679546e5d7f54563e02866688e75c6e9508b544a0cfc.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": "6a0c6a3698c2e26e8bf955cbb9bc790df6165c696205f80c971e1d876a3def59", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "38973f884d48546d8a1df823cf858dcf513c5dd4f41786df32956ec79537f57a", "generation_seconds_batch": 14.55058903596364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2801816463470459, "target_z": -0.2988281020934421, "ce": 5.863759994506836, "genuineness": 4.770940780639648, "identity": 0.492681086063385, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6a0c6a3698c2e26e8bf955cbb9bc790df6165c696205f80c971e1d876a3def59.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "6a1508a49755ff15b0d534303539bbf221f6725c3dffd41443fbb3c842f624b1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "108cbf2c30b77b6b87efe167cd86a961280ccebcc342ad3f84c215e03bc37e35", "generation_seconds_batch": 19.292222357937135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21717050671577454, "target_z": -0.38867186603656434, "ce": 5.7684478759765625, "genuineness": 4.7332844734191895, "identity": 0.7099006175994873, "hypothesis": "La porte 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_Disappointment/6a1508a49755ff15b0d534303539bbf221f6725c3dffd41443fbb3c842f624b1.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": "6a19abe1a0fc9cb4dd7b537e26b84f9cfee86eef9de642010dfa1adf7658e94d", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "306472ee5d5d1fbd9abb8cc2358b6f3bebe0000ddc55b3681001bac599b12f4a", "generation_seconds_batch": 15.169827741920017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.889745831489563, "target_z": 0.5703125146070803, "ce": 5.442798614501953, "genuineness": 4.557555198669434, "identity": 0.6631290316581726, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi à quoi nous pourrons parler.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6a19abe1a0fc9cb4dd7b537e26b84f9cfee86eef9de642010dfa1adf7658e94d.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "6a4fe9eb1149dea1c4bcd7c92b20f9e1963a70654c98314575606a52f4f6cf32", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1e0d2fc1917124f4cfe64a5ec3a9f12d2a1739e597ce036d5873c7e9b4999ccd", "generation_seconds_batch": 19.29934238793794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46647539734840393, "target_z": -0.03320313661926848, "ce": 5.315715789794922, "genuineness": 4.65797233581543, "identity": 0.8006842136383057, "hypothesis": "J'ai trouvé la 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_Disappointment/6a4fe9eb1149dea1c4bcd7c92b20f9e1963a70654c98314575606a52f4f6cf32.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eda2b3ea8040c354e7f2ef02e13c3f49a4a4f25e6d0b1098f524af751926cd1e", "generation_seconds_batch": 16.053690223954618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07334074378013611, "target_z": -0.5937500053116656, "ce": 6.419747352600098, "genuineness": 3.9676074981689453, "identity": 0.32517653703689575, "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_Disappointment/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "6ab54d6463b63ad5c7752e7cdf39c3b0f431b23198ee582a0afa0d512c1ea35b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "25261fa1a35bccfd82c254f3b09684c649aca5476c0355ba3fae7b56701e5b53", "generation_seconds_batch": 19.367453283979557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41031330823898315, "target_z": -0.11328125464770739, "ce": 5.605623245239258, "genuineness": 4.469690799713135, "identity": 0.5808207988739014, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6ab54d6463b63ad5c7752e7cdf39c3b0f431b23198ee582a0afa0d512c1ea35b.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "6b7d7ec0a54ca662b8643c7c13d166bf8ce67d1d973fd4f0195b59289a468240", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d4a100607ae0a9ceb97902d56a1ada497bf4f3192d823f6053c557f956bb78c6", "generation_seconds_batch": 19.39733100903686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21306106448173523, "target_z": -0.39453127058270415, "ce": 5.756534099578857, "genuineness": 4.6203155517578125, "identity": 0.7791440486907959, "hypothesis": "J'ai trouvé la 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_Disappointment/6b7d7ec0a54ca662b8643c7c13d166bf8ce67d1d973fd4f0195b59289a468240.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "94ac02bbaf5aad8d213709b06f46851dd6ed15fff3d81fcdd3367722a070985e", "generation_seconds_batch": 15.76232750795316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20758184790611267, "target_z": -0.402343753319791, "ce": 6.268836498260498, "genuineness": 4.595211505889893, "identity": 0.6632235050201416, "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_Disappointment/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.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": "6b9c6ba4b4fdd38cb8f5641b5b3d234704c349b941ea6945231e2888e2e9526b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "df72377567cc1b1d152a1d4446cfa9b0f83eaf8f8ce34e608ace117a0548d3c3", "generation_seconds_batch": 19.69398797105532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2774420380592346, "target_z": -0.3027343434619856, "ce": 5.903473377227783, "genuineness": 4.507347106933594, "identity": 0.6164501905441284, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6b9c6ba4b4fdd38cb8f5641b5b3d234704c349b941ea6945231e2888e2e9526b.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": "6bb62505ace95681ff51ff50f8f85b0695a084d903fe7e6e96c59815e8a6c70c", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8a82aecd69317d96020f7b3c800be8eb7e0784f524f8d65001ec62a0be3881ee", "generation_seconds_batch": 15.164338810020126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27059298753738403, "target_z": -0.31249998937666884, "ce": 5.538110733032227, "genuineness": 4.545003414154053, "identity": 0.6691333055496216, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6bb62505ace95681ff51ff50f8f85b0695a084d903fe7e6e96c59815e8a6c70c.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "6ccf46bd7333496c0efb4c73d1c76cdc82f1fd528d0febc1ad3da77947b01990", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d2e64d67a6f76f55001875203d1782da92607993aefde07f8d78d9ad2bfcefcd", "generation_seconds_batch": 19.21610655693803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1801857054233551, "target_z": -0.4414062519918746, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.3930545449256897, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6ccf46bd7333496c0efb4c73d1c76cdc82f1fd528d0febc1ad3da77947b01990.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "6cf0215f9679d40770d060a2c81cf0c4aaede7ef5ad0ebb3e0c870c335b72621", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ea10cd56366984f5cc0df5e97daee45cfcf97ea32ef278eebf51df818d5d3ea9", "generation_seconds_batch": 19.27418991003651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.034986138343811035, "target_z": -0.6484375119512475, "ce": 6.284721851348877, "genuineness": 4.68307638168335, "identity": 0.4340544044971466, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6cf0215f9679d40770d060a2c81cf0c4aaede7ef5ad0ebb3e0c870c335b72621.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "6da015b183da2fe53077d8ad983a3a9ca2e77bf191fc3caa0137a901f7b43076", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2f58199cd8a0410121e558b2df668e6f40875cf16d989dd74bd12b8b2c9dc0d6", "generation_seconds_batch": 19.613883769023232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4555169343948364, "target_z": -0.04882814458676687, "ce": 5.446769714355469, "genuineness": 4.557555198669434, "identity": 0.648236095905304, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6da015b183da2fe53077d8ad983a3a9ca2e77bf191fc3caa0137a901f7b43076.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "6dac448f9c4efa51fe811a09d63da642bb587aec1425c395195ad40362202edf", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "48d623be6980addac6bcf9b968f96ff4322b832f6bb96d6697c7388fdcf74d96", "generation_seconds_batch": 19.284784403978847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07881999015808105, "target_z": -0.585937480081254, "ce": 6.078212261199951, "genuineness": 3.9425034523010254, "identity": 0.3137972056865692, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6dac448f9c4efa51fe811a09d63da642bb587aec1425c395195ad40362202edf.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "6e0e488d363fc9a7029299cea7878ab0097e619d292c284af5a4a3f66cfe7102", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dfadbfe81d6c2a8594b8478f09a94d69cafaaecad3d377ba3be36029d8091a6d", "generation_seconds_batch": 14.439944087993354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2829212546348572, "target_z": -0.29492186072489873, "ce": 6.125868320465088, "genuineness": 4.381826400756836, "identity": 0.5318373441696167, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6e0e488d363fc9a7029299cea7878ab0097e619d292c284af5a4a3f66cfe7102.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "6e30eea2de506e0b91ca2d78f2fdb466ceb2c11f98158b5e8feb34a950f79409", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fd0d107d2578c16fbffdac685b5273041d292830859f9296491ac1c16017575c", "generation_seconds_batch": 14.397154332953505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14868015050888062, "target_z": -0.48632811271677334, "ce": 6.141753673553467, "genuineness": 4.7081804275512695, "identity": 0.803014874458313, "hypothesis": "J'ai trouvé la 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_Disappointment/6e30eea2de506e0b91ca2d78f2fdb466ceb2c11f98158b5e8feb34a950f79409.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "6e97a814f12a4e5c0953c7a9ca31e55b818a2c8cc9b25001a7ad88be2a830b99", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "752b0fb341cdc84c13d72d8851122847d06659587d49dbd8daf600017354eb09", "generation_seconds_batch": 19.575114086968824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12265381217002869, "target_z": -0.5234374907045852, "ce": 6.181467056274414, "genuineness": 4.8588056564331055, "identity": 0.6674838662147522, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6e97a814f12a4e5c0953c7a9ca31e55b818a2c8cc9b25001a7ad88be2a830b99.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "6eb0c598da0c3f64cc9fb8426f4c6373be2e04c5251ed8eef58cb1c56725a1e8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "88afa5094df16efc40b6afd9aee8f829acc8f365e1ff4ff2d83896826de31a41", "generation_seconds_batch": 22.193127745995298, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 5.982900142669678, "genuineness": 4.632867813110352, "identity": 0.4096311628818512, "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_Disappointment/6eb0c598da0c3f64cc9fb8426f4c6373be2e04c5251ed8eef58cb1c56725a1e8.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "6ed6e3f6d22146ecf91302e30ca25ac0f4a5964ab60c5b5b2b3aeded4f3b17fd", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "17a2cecfa8d6ad162a592f2957ef2eff88286e7a76b61178f8136438c2279f76", "generation_seconds_batch": 19.018552226014435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33154940605163574, "target_z": -0.22558592770661656, "ce": 5.6413655281066895, "genuineness": 4.394378662109375, "identity": 0.4444716274738312, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond aast dit oude raam. We kunnen er samenheen kijken.", "wer": 0.2222222222222222, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6ed6e3f6d22146ecf91302e30ca25ac0f4a5964ab60c5b5b2b3aeded4f3b17fd.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "6f2792353d1d47947794ab3a7e3b0d59083159d4fbe556761f65afc396da3e85", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5b6cf6aae7cb3b5731fcb7a2186371f7f998e372ff5cb0ae734338c4773a9463", "generation_seconds_batch": 19.15356204006821, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20758184790611267, "target_z": -0.402343753319791, "ce": 6.038498878479004, "genuineness": 4.7332844734191895, "identity": 0.6368632316589355, "hypothesis": "J'ai trouvé la 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_Disappointment/6f2792353d1d47947794ab3a7e3b0d59083159d4fbe556761f65afc396da3e85.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "6f2cc282367faf614025a335de2eb4ebac8a4a0aa63fcfb996bab1e6c1204e33", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a5c1cf7560e1692ecf11c18201a3e029258ff15dc3255a6bd27be526ddf03e9e", "generation_seconds_batch": 19.09775927697774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.313057005405426, "target_z": -0.2519531206842717, "ce": 5.990842819213867, "genuineness": 4.7458367347717285, "identity": 0.7307473421096802, "hypothesis": "La porte 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_Disappointment/6f2cc282367faf614025a335de2eb4ebac8a4a0aa63fcfb996bab1e6c1204e33.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "6fb997fec70909c7768573d60c2f1a0bc93dde59d2fb1dddb4b12353c95ff65f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "863750ada4562c031befe73de1360506d2b1d3f7226ff31f067344e216f7d975", "generation_seconds_batch": 19.137558708083816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2089516520500183, "target_z": -0.4003906326355193, "ce": 5.831989288330078, "genuineness": 4.65797233581543, "identity": 0.6396603584289551, "hypothesis": "La porte 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_Disappointment/6fb997fec70909c7768573d60c2f1a0bc93dde59d2fb1dddb4b12353c95ff65f.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "6fc0202a7e7ef5360dc3de2950815fb2aa682b1333da48b1d944f16c2f2e232e", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c075b0f070d84f2592216fcd9b590af3927c81e3d0a5c9ed3077f97a5f33b8a6", "generation_seconds_batch": 18.18502020498272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07334074378013611, "target_z": -0.5937500053116656, "ce": 6.419747352600098, "genuineness": 4.68307638168335, "identity": 0.6355540752410889, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/6fc0202a7e7ef5360dc3de2950815fb2aa682b1333da48b1d944f16c2f2e232e.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "70a504d7884a47357cd74ed73cdcb1673ef2a41546618ee39f7f557301545911", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "78072cdb48ef56f6fbd786bbc88a71a9dc463d718c4f9323347fa10aede4baa5", "generation_seconds_batch": 14.124280603020452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5288016200065613, "target_z": 0.05566404573505548, "ce": 5.569881439208984, "genuineness": 4.7458367347717285, "identity": 0.5151607990264893, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/70a504d7884a47357cd74ed73cdcb1673ef2a41546618ee39f7f557301545911.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": "712e2ab37468203b2d9aadd79976a1fb8fbc7def93ee5bad999887757709f6cc", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d36a9dcdfa45e550de5d8bd1c901eb409170c5282d93e5f57e0594745e6a8572", "generation_seconds_batch": 19.206959026982076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5383902788162231, "target_z": 0.06933593301828216, "ce": 5.736677646636963, "genuineness": 4.7332844734191895, "identity": 0.4486699104309082, "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_Disappointment/712e2ab37468203b2d9aadd79976a1fb8fbc7def93ee5bad999887757709f6cc.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "71c54e75ee9a6f77e0ca4c833f4fd09ff6c17c3c5dc7e4720ba1745902a57676", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a9c1a07b4f6db36ec076488126f726cc0b30ef9be9e3ae8492637f18e1b9bb8c", "generation_seconds_batch": 19.012331202975474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1404612958431244, "target_z": -0.4980468793157283, "ce": 5.669164657592773, "genuineness": 4.595211505889893, "identity": 0.528151273727417, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/71c54e75ee9a6f77e0ca4c833f4fd09ff6c17c3c5dc7e4720ba1745902a57676.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "7236da6603bb1bee52781fd5d9d2ca35c4cc9d5494c901dfd8c7669f5f9315d0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b002051bd74c2adfa45b7cee5bfe1ef5a0b252c5d993fd47b102ffaa508fa081", "generation_seconds_batch": 19.004502539988607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1692272424697876, "target_z": -0.457031259959373, "ce": 6.1894097328186035, "genuineness": 4.432034492492676, "identity": 0.2525423467159271, "hypothesis": "The 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_Disappointment/7236da6603bb1bee52781fd5d9d2ca35c4cc9d5494c901dfd8c7669f5f9315d0.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "7309a8f46c66486dedb6453f3b29f9b566ad7c7fc7ef283725b4db7d86339c31", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65dca467eb466eaa49a013aa6989c1b71b03849d00dc4cfcd0bded2440abbf71", "generation_seconds_batch": 14.69353727903217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8733081221580505, "target_z": 0.5468749814091705, "ce": 5.95112943649292, "genuineness": 4.381826400756836, "identity": 0.6190839409828186, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/7309a8f46c66486dedb6453f3b29f9b566ad7c7fc7ef283725b4db7d86339c31.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": "73228f3d64532224f189da9cda2cab4c4a31676546f9014cca9a4e703c485e69", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d6e7d9a2c5ab19981957c8baf2ba78965d2f38a67fcce8c44b24cbd839dbf31d", "generation_seconds_batch": 15.1648919750005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32538527250289917, "target_z": -0.23437499203250162, "ce": 5.4666266441345215, "genuineness": 4.432034492492676, "identity": 0.8020694851875305, "hypothesis": "Les clés sont sur la table de la cuisine j'ai regardé dans le tiroir et puis près de la fenêtre prends-les quand tu partiras.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/73228f3d64532224f189da9cda2cab4c4a31676546f9014cca9a4e703c485e69.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "7339fbf259a60a1edd8a6923d612f6c26a4a93937070ef4a913b0e7fb25ce099", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a6aa447ee8b7fa69671f0b377db939ee6b071d6afca1cccd28f685ab685f56da", "generation_seconds_batch": 20.588070267927833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16374802589416504, "target_z": -0.46484374269645984, "ce": 5.982900142669678, "genuineness": 4.6203155517578125, "identity": 0.8278024792671204, "hypothesis": "J'ai trouvé la 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_Disappointment/7339fbf259a60a1edd8a6923d612f6c26a4a93937070ef4a913b0e7fb25ce099.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": "73431d603fb5944356137f2aa84f04187892f2a1d70a1bac6c3c6c1a31383102", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "476a3fe73fcde5a443bd1e438014138b7b87d27a8a45745595c46591dff07bdf", "generation_seconds_batch": 20.399317879928276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22812896966934204, "target_z": -0.37304685806906596, "ce": 5.855817794799805, "genuineness": 4.65797233581543, "identity": 0.5112891793251038, "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_Disappointment/73431d603fb5944356137f2aa84f04187892f2a1d70a1bac6c3c6c1a31383102.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": "7354847ef78666844879e651259369d944f73b567b724562229239518a4a0a82", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1a3a8f8d65c05456e8b202dd5c36a93e072f1abb83b6ec12fa4ce5b4d7f083e", "generation_seconds_batch": 15.449887205963023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1911441683769226, "target_z": -0.4257812440243762, "ce": 5.911416053771973, "genuineness": 4.281409740447998, "identity": 0.32265567779541016, "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_Disappointment/7354847ef78666844879e651259369d944f73b567b724562229239518a4a0a82.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "73b198962b623a48a892f009521965bbd0f36f7adf39c3254fc50e0c69fa7510", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "61aaa7f68e3da5af14d4435ba2f953652086216b13de721877c02f69a363968b", "generation_seconds_batch": 22.49775681993924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1938837766647339, "target_z": -0.4218750026558328, "ce": 5.998785495758057, "genuineness": 4.8588056564331055, "identity": 0.6940827369689941, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/73b198962b623a48a892f009521965bbd0f36f7adf39c3254fc50e0c69fa7510.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "7422f94998972ed23904aca48ae04745672e5e95310ead230fa646842c0a4268", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ce4d473af1f51b59c5e376d08d5980d68ae568ad9f07d1a95f08abfb2e68412e", "generation_seconds_batch": 19.049944333033636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12813302874565125, "target_z": -0.5156250079674984, "ce": 5.816103935241699, "genuineness": 4.720732688903809, "identity": 0.44640403985977173, "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_Disappointment/7422f94998972ed23904aca48ae04745672e5e95310ead230fa646842c0a4268.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "7447b813606df62bff69b95b092ff26d7ada3811812379f322ff41dc90014d4f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ae58401234e5817adbefa2ca20b042014c4ff79c608f4ae768b607411743d3c2", "generation_seconds_batch": 19.006341258995235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13635188341140747, "target_z": -0.5039062413685435, "ce": 6.078212261199951, "genuineness": 4.720732688903809, "identity": 0.5439635515213013, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/7447b813606df62bff69b95b092ff26d7ada3811812379f322ff41dc90014d4f.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "7470e2a7303735361b04dac6e647e133dacade5dfea2ba9c5c41c1fbfad9a96f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3217476ca163ac55e74c26e7cebc70a833b8029fbfb1a3494f2f376788612245", "generation_seconds_batch": 19.913251132005826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15278956294059753, "target_z": -0.4804687506639582, "ce": 5.959072113037109, "genuineness": 4.469690799713135, "identity": 0.6712024807929993, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/7470e2a7303735361b04dac6e647e133dacade5dfea2ba9c5c41c1fbfad9a96f.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "74ce9a610fc3b72d6c4967118127be8efcab3da71b78896681d2fb0e5326c67a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af701bbbd7bc381bb7c7042aeb35e3cf2667f813fb53c964bff0cf8460ddb0a0", "generation_seconds_batch": 22.086988972965628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27881181240081787, "target_z": -0.30078126527103854, "ce": 5.855817794799805, "genuineness": 4.720732688903809, "identity": 0.8927067518234253, "hypothesis": "La porte 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_Disappointment/74ce9a610fc3b72d6c4967118127be8efcab3da71b78896681d2fb0e5326c67a.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "755ba2560f8e4d8a514d2c61884e4da1341c32f19ad957fc4afafae8023315b2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ec6c22a617269c293d767fcf37b249924386cf2ee0b39cde554001ad7f86e32", "generation_seconds_batch": 19.388688307022676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0048096179962158, "target_z": 0.7343749920325016, "ce": 6.038498878479004, "genuineness": 4.607763767242432, "identity": 0.5358058214187622, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/755ba2560f8e4d8a514d2c61884e4da1341c32f19ad957fc4afafae8023315b2.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "75cd4a44a746652881a0d5dba55920da1576601a5eb0ba3f461e59b4fef2740d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ed43898aec7808ad09a7e8f4801a45a8a0c57f41c7f6a9ba6d5e85098c235778", "generation_seconds_batch": 20.990185511065647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04046538472175598, "target_z": -0.640624986720836, "ce": 6.38003396987915, "genuineness": 4.7332844734191895, "identity": 0.7835160493850708, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/75cd4a44a746652881a0d5dba55920da1576601a5eb0ba3f461e59b4fef2740d.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": "75d5d8e447ba6068a3258d3168c0ebad40264f8649ba713e69299df45dbd7a0e", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9be4f84ef025c67286e64dc5d9ea302fc3280632ac195e6a626048311e9ca065", "generation_seconds_batch": 19.48368712689262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22812896966934204, "target_z": -0.37304685806906596, "ce": 5.998785495758057, "genuineness": 4.7834930419921875, "identity": 0.7347362041473389, "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_Disappointment/75d5d8e447ba6068a3258d3168c0ebad40264f8649ba713e69299df45dbd7a0e.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": "767f648c01b3a8815989f07fcd3a35d53b039e26e26d4a7ddaa0b2990b87d4a8", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12cd28f13f0689812b1f59ee5221e24cc32e0d3a1d7e8fa04fa6cccd6d30ddf0", "generation_seconds_batch": 14.635168944019824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22812896966934204, "target_z": -0.37304685806906596, "ce": 5.847874641418457, "genuineness": 4.557555198669434, "identity": 0.5953525304794312, "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_Disappointment/767f648c01b3a8815989f07fcd3a35d53b039e26e26d4a7ddaa0b2990b87d4a8.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "76b17529160823f0b8082aa9f7aa9fe238f667cfebbe77e2237bacb773758bc1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4b7fbe51b8ff993597748585f53d46b22a7e87478c1949d6d9bfb05ebf3cf70a", "generation_seconds_batch": 19.09745725407265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22127991914749146, "target_z": -0.3828125039837492, "ce": 6.117925643920898, "genuineness": 4.331617832183838, "identity": 0.3684709072113037, "hypothesis": "The 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_Disappointment/76b17529160823f0b8082aa9f7aa9fe238f667cfebbe77e2237bacb773758bc1.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "774c5f4b915de7583065c0e2f779f67e651f1bd5fabd7bfa2c5069bee9488200", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a16cfb1ce7def620bed0d840bab97ab713c6b92a3952714858916058e3236f94", "generation_seconds_batch": 19.155882952036336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16100841760635376, "target_z": -0.46874998406500323, "ce": 5.808161735534668, "genuineness": 4.871357440948486, "identity": 0.770133912563324, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/774c5f4b915de7583065c0e2f779f67e651f1bd5fabd7bfa2c5069bee9488200.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "777fdffc61ea1feab9ee22e6a1ae020edb8944d8cd09b300b1340d8c712908c7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1e6c5c258dc76f5ac990d3f9e8164979128c72b4ed6fada53c87b08345e4a7ac", "generation_seconds_batch": 22.248959227930754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4445585012435913, "target_z": -0.06445311006094052, "ce": 5.935244083404541, "genuineness": 4.494794845581055, "identity": 0.42723774909973145, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/777fdffc61ea1feab9ee22e6a1ae020edb8944d8cd09b300b1340d8c712908c7.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "5a6f1fac4ebb274e60190e26ca82ca1c3c7512138646c041e849484f2dd2d580", "generation_seconds_batch": 14.497203449020162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17607629299163818, "target_z": -0.44726561404468973, "ce": 6.1020402908325195, "genuineness": 4.381826400756836, "identity": 0.753581702709198, "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_Disappointment/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.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": "77c3f47eed91cef360ae7418aa6efeacc4367db164c0a59bc5a7a8cfbf482d8f", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "403e31f6221fd4183daa3fbb8bccc88e9d3e19317dae31e9cd2d388f55ba1943", "generation_seconds_batch": 14.472954318975098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1979931890964508, "target_z": -0.41601564060301766, "ce": 6.046441555023193, "genuineness": 4.6956281661987305, "identity": 0.671242356300354, "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_Disappointment/77c3f47eed91cef360ae7418aa6efeacc4367db164c0a59bc5a7a8cfbf482d8f.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "78b21ee8ab4196ff4d6001a2b1818929b9a1a98381e3951f9eb417e61a9e7eec", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c2d61d27273004b4a0821ff0289b6a41269c622b62236072bf4f14ef8498d79f", "generation_seconds_batch": 19.13074116304051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18292531371116638, "target_z": -0.43750001062333116, "ce": 5.546053409576416, "genuineness": 4.934117794036865, "identity": 0.6863072514533997, "hypothesis": "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_Disappointment/78b21ee8ab4196ff4d6001a2b1818929b9a1a98381e3951f9eb417e61a9e7eec.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "7923a7f46f1d6c4db6859b6d451afe94bf6dc653c1f66f7f5cf938ffa1bd02e8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0610984014decb4cd93674e2bf3eb1c86e2020d0549bfc52e894c0b0b137baa7", "generation_seconds_batch": 15.234508499968797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12539342045783997, "target_z": -0.5195312493360418, "ce": 6.260893821716309, "genuineness": 4.68307638168335, "identity": 0.48749563097953796, "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_Disappointment/7923a7f46f1d6c4db6859b6d451afe94bf6dc653c1f66f7f5cf938ffa1bd02e8.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "7695835e82ea44c574c8f6e57fd8dd86d743215110ef9ba76a2d80c82dfff473", "generation_seconds_batch": 18.378899276955053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16374802589416504, "target_z": -0.46484374269645984, "ce": 6.09409761428833, "genuineness": 4.293961524963379, "identity": 0.7059427499771118, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de laag en daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "79a546b737718f0883f6113155c1b9ad2c5741093bd91cedb7460874e88912a0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6529c1b66b956c17e02a2fa2a1261eee1211df76afc809b41084d265a01c05b4", "generation_seconds_batch": 19.123189495061524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0376849174499512, "target_z": 0.7812498884550226, "ce": 5.808161735534668, "genuineness": 4.494794845581055, "identity": 0.3317837119102478, "hypothesis": "De deur staat nog open. Ik heb je 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_Disappointment/79a546b737718f0883f6113155c1b9ad2c5741093bd91cedb7460874e88912a0.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": "79fd68f237f7e3d2e43a88a671d4f6b060aa875a00635112d11783d87b6291a7", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2cd3fb3f8e93327998da9b2401f37a8c5aedf130bf552be8961a04ffe5bcbb2", "generation_seconds_batch": 14.698859486030415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7308481931686401, "target_z": 0.3437500053116656, "ce": 5.657250881195068, "genuineness": 4.532451152801514, "identity": 0.5828930139541626, "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_Disappointment/79fd68f237f7e3d2e43a88a671d4f6b060aa875a00635112d11783d87b6291a7.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "7a06c75b1b6a55fb6e0c4e5e2701e5c7fcd1dfde96874fc1390f1b63fd183998", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c35ffd5c7e4f2cfa4edf62cabccfbd94ef12c5f5d9d8923a3d2245fc2e6df4b0", "generation_seconds_batch": 19.456832692958415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3801775574684143, "target_z": -0.15624999468833442, "ce": 5.49045467376709, "genuineness": 4.7834930419921875, "identity": 0.5603729486465454, "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_Disappointment/7a06c75b1b6a55fb6e0c4e5e2701e5c7fcd1dfde96874fc1390f1b63fd183998.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "7a25c07ba238ab89876c3e9d7adca4bb9a8a8189b97d6e87ad6334247b81589d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "59111c8a82ed35e4f0332ae9aed25467f8e2801ca676246c2e61b1f7918b3500", "generation_seconds_batch": 22.451061881962232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2555251121520996, "target_z": -0.33398435939698234, "ce": 5.863759994506836, "genuineness": 4.519899368286133, "identity": 0.3995668292045593, "hypothesis": "The 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_Disappointment/7a25c07ba238ab89876c3e9d7adca4bb9a8a8189b97d6e87ad6334247b81589d.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "7a25e4e30a249b6c8250a9f6ebda34c683b3508a94249ef8f3d417152f6a1e58", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bb1bf92e37dad15dc3ad9c42a3ce29023c2639d34411779d7449e8bc833fe1a1", "generation_seconds_batch": 14.395342324045487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28155142068862915, "target_z": -0.29687502390249515, "ce": 6.1894097328186035, "genuineness": 4.6203155517578125, "identity": 0.5101797580718994, "hypothesis": "The 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_Disappointment/7a25e4e30a249b6c8250a9f6ebda34c683b3508a94249ef8f3d417152f6a1e58.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "7a260b67a68accb7204db019569260c78e8387fa27a4547167e8e9b5bd8c6bb3", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "18978e034def3ca742385fe08d8bd7c547ddd3c0086fa8bbff21a5cf096768f3", "generation_seconds_batch": 15.717827829066664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12539342045783997, "target_z": -0.5195312493360418, "ce": 6.133810997009277, "genuineness": 4.7081804275512695, "identity": 0.8274907469749451, "hypothesis": "J'ai trouvé la 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_Disappointment/7a260b67a68accb7204db019569260c78e8387fa27a4547167e8e9b5bd8c6bb3.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "7a8f4c780891ade98a77a90d004041dded4640479e60ce6fa33ab4f610675042", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bf3ce7d98e4184c593f9448bb89e3f6ed11ac42fe24a7b5e8295bdcdebd7a227", "generation_seconds_batch": 19.367453283979557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32401543855667114, "target_z": -0.23632815521009803, "ce": 5.911416053771973, "genuineness": 4.582659721374512, "identity": 0.5996111631393433, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/7a8f4c780891ade98a77a90d004041dded4640479e60ce6fa33ab4f610675042.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": "7c0213d405e79e04cda0e6454d995b0e605ddaba2f242db044ab5c2a55a7d0fc", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e37efadccf5449c2a7846612173672343cacb923074a06efd97b4a9dab4375c", "generation_seconds_batch": 19.385573319043033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3911360204219818, "target_z": -0.14062498672083604, "ce": 5.486483573913574, "genuineness": 4.545003414154053, "identity": 0.6655120849609375, "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_Disappointment/7c0213d405e79e04cda0e6454d995b0e605ddaba2f242db044ab5c2a55a7d0fc.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "7c0c16021149f52fc4ec10752f8523ad7ef4c4e981bd4966477d0fdb0b21f5f7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "168df49759c5089dbbf90a385bf62b89979ad06c214b3b284ae5c9992f1b53b4", "generation_seconds_batch": 19.613883769023232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31031739711761475, "target_z": -0.2558593620528151, "ce": 5.71682071685791, "genuineness": 4.846253395080566, "identity": 0.7341709136962891, "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_Disappointment/7c0c16021149f52fc4ec10752f8523ad7ef4c4e981bd4966477d0fdb0b21f5f7.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "7ca1fe1edde7ee6970047eb19cf316babe67c14962c701a4dcb3ab2c5cedd151", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "812daa48a5e951bfc3ec5e2672681d8a0bdd0c91d422cd4846a9827483150581", "generation_seconds_batch": 19.575114086968824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10621613264083862, "target_z": -0.5468749814091705, "ce": 6.141753673553467, "genuineness": 4.645420074462891, "identity": 0.8509795665740967, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/7ca1fe1edde7ee6970047eb19cf316babe67c14962c701a4dcb3ab2c5cedd151.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "7cebae0d94ea73aa4dd2572eec4e17d462e4a3d2f3472314f3d43ec59d9bb955", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2ed50b3c78f9482594ee5c20838dc532f938bb65fdb92ae49fe80016f554d7d4", "generation_seconds_batch": 19.04896215593908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7212595343589783, "target_z": 0.3300781180284389, "ce": 6.078212261199951, "genuineness": 4.632867813110352, "identity": 0.5063279271125793, "hypothesis": "De deur 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_Disappointment/7cebae0d94ea73aa4dd2572eec4e17d462e4a3d2f3472314f3d43ec59d9bb955.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "7cf68fd8b2ab8a6eefe8b07de25ee4ce04a7463f5c69e72b285b9bca6a28350e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "73a08671f8a730c4bfe45cbf354c1ac4c812d0662ab81faa46d1b5c69fde9283", "generation_seconds_batch": 19.880609962972812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.674686074256897, "target_z": 0.26367184478990197, "ce": 6.197352409362793, "genuineness": 4.457139015197754, "identity": 0.7208397388458252, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/7cf68fd8b2ab8a6eefe8b07de25ee4ce04a7463f5c69e72b285b9bca6a28350e.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": "7d24811ef52988522bc1ef3a78b8b513c91ed15d5d16acedd7797e6d343ce215", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a50ed3b982a24243ab8d6c734d6bb9d3afa518c7eb092bfb7e8b9eb7d3733130", "generation_seconds_batch": 19.372340533998795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2336081862449646, "target_z": -0.3652343753319791, "ce": 5.692992687225342, "genuineness": 4.6705241203308105, "identity": 0.6515824794769287, "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_Disappointment/7d24811ef52988522bc1ef3a78b8b513c91ed15d5d16acedd7797e6d343ce215.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "7d42d520bfb9b806d589deccbe52158429ec4d92f33d48ddb230e354936d88a4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "38af01baaee3d23b1b4f9521a6338b850d6c1fdf48adfd5c49127c54ce58fe77", "generation_seconds_batch": 23.47681622894015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17744609713554382, "target_z": -0.445312493360418, "ce": 5.919358730316162, "genuineness": 4.306513786315918, "identity": 0.4473782181739807, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/7d42d520bfb9b806d589deccbe52158429ec4d92f33d48ddb230e354936d88a4.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": "7d5751bc650be28777ae8be6fd34918e11c80f5090ac2236207f16bc5d75e16a", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c0415432a03399210a46c30cd92e238a3fcd660a2d5e54c0fcb9b8a500dbac67", "generation_seconds_batch": 19.678380422992632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1514197587966919, "target_z": -0.4824218713482299, "ce": 5.77639102935791, "genuineness": 4.162164688110352, "identity": 0.3764817714691162, "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_Disappointment/7d5751bc650be28777ae8be6fd34918e11c80f5090ac2236207f16bc5d75e16a.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "7da69f2dcd9ab3fa36400b6e450f00765acc3c5bf683ee3ccdb0ba1d07c6d447", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e104812219b180f9615ffad813de29d89b4b428fcaba43710bccda7df7996836", "generation_seconds_batch": 15.822194532025605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1870347559452057, "target_z": -0.43164060607719135, "ce": 5.903473377227783, "genuineness": 4.319066047668457, "identity": 0.5839991569519043, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/7da69f2dcd9ab3fa36400b6e450f00765acc3c5bf683ee3ccdb0ba1d07c6d447.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "7e1c2d4958bfcceeadf77a835b1026f7a1e45a840469be026c361f92848102f0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f7e8ae4ea411abef67b91e8de5ece08e6b182221c9fcc41f68eff747b1b71c12", "generation_seconds_batch": 22.045023040962406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13909149169921875, "target_z": -0.5, "ce": 6.086154937744141, "genuineness": 4.457139015197754, "identity": 0.42857712507247925, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/7e1c2d4958bfcceeadf77a835b1026f7a1e45a840469be026c361f92848102f0.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "7ecebf60a8d8b853a220df07e6788c5dd4bc4fa40ac5f9b41856fad07c41edcf", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "83a1511b5f646be402886c4f5fe16cddda05e81a672ef03c9bea2bfc47d5bbbd", "generation_seconds_batch": 19.25128011102788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1336122751235962, "target_z": -0.5078124827370868, "ce": 5.863759994506836, "genuineness": 4.808597087860107, "identity": 0.5908175110816956, "hypothesis": "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_Disappointment/7ecebf60a8d8b853a220df07e6788c5dd4bc4fa40ac5f9b41856fad07c41edcf.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "7f60eb0383e68475c5f9fc6fdcad139f88143c4a4761bf27fdf3b0033c5c49df", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7a9eda2f6459705fdb268824dd6abdca359106dcd4cc035b53d9e186f192006a", "generation_seconds_batch": 14.532412442960776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17059704661369324, "target_z": -0.45507813927510127, "ce": 6.125868320465088, "genuineness": 4.921566009521484, "identity": 0.6053822040557861, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/7f60eb0383e68475c5f9fc6fdcad139f88143c4a4761bf27fdf3b0033c5c49df.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": "7f6b28f8f3c7145d06948edb2ef3e81700d721b257eb3bd2184f363cd0d1871a", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f59aa59bba5836927a4a47cdc9db846e043378b6ff887163c47e7500e408ff7b", "generation_seconds_batch": 14.340960153960623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22401952743530273, "target_z": -0.37890626261520577, "ce": 6.038498878479004, "genuineness": 4.3881025314331055, "identity": 0.6170791387557983, "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_Disappointment/7f6b28f8f3c7145d06948edb2ef3e81700d721b257eb3bd2184f363cd0d1871a.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6785c2a4361e1634e1f8049e292d839f3c575815dbe741a43f99799bceb8621", "generation_seconds_batch": 14.482601386960596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1555291712284088, "target_z": -0.47656250929541477, "ce": 6.419747352600098, "genuineness": 4.607763767242432, "identity": 0.23868301510810852, "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_Disappointment/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "7fcf40e90b7dc4d948467dfb58a85ae0e9a44be586b48cd3536be101e0272ff6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1c72e2e3ab7f01e3486a58de178fca0fc81529cefda557e6caa1fa863e1e72a1", "generation_seconds_batch": 14.404255851055495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27470239996910095, "target_z": -0.3066406273238537, "ce": 5.974957466125488, "genuineness": 4.557555198669434, "identity": 0.6445155143737793, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/7fcf40e90b7dc4d948467dfb58a85ae0e9a44be586b48cd3536be101e0272ff6.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "4947c31baf79e686863ced82fa94424eb7fa0dbe8154b613060c2ec5ab272974", "generation_seconds_batch": 16.50172446295619, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1801857054233551, "target_z": -0.4414062519918746, "ce": 6.24500846862793, "genuineness": 4.507347106933594, "identity": 0.6330311298370361, "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_Disappointment/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "80cbaf7180a0d418437d5daca69688064e9232f7286ac25880ea2be610878afd", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e2328495dcf7accd1b97d65b2d101f6a430be743c4a11ebdeeaeea8f9d0ef24f", "generation_seconds_batch": 21.96375277696643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.355521023273468, "target_z": -0.1914062519918746, "ce": 5.847874641418457, "genuineness": 4.482243061065674, "identity": 0.698067843914032, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/80cbaf7180a0d418437d5daca69688064e9232f7286ac25880ea2be610878afd.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "80fd3821a4894e1053731c272c601ef71273b27311be923468480993c7bb82fe", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c508b90b39fa3cb6b276419b340db33a77a6f99694f021b2f29cf3c02c7f363c", "generation_seconds_batch": 14.299811575911008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2158007025718689, "target_z": -0.390624986720836, "ce": 5.4825119972229, "genuineness": 4.570107460021973, "identity": 0.5161213874816895, "hypothesis": "The 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_Disappointment/80fd3821a4894e1053731c272c601ef71273b27311be923468480993c7bb82fe.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "8206fe9ee7ad7c8b9a3fd87508bf04b59d07594a443bcf683b03c260fb63a27b", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8825adfe3ad1d3e2aec30104d01c413c1c052a762dfb7fc4cc93a7a707cc4410", "generation_seconds_batch": 16.075285686994903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16648763418197632, "target_z": -0.4609375013279164, "ce": 6.2767791748046875, "genuineness": 4.331617832183838, "identity": 0.19571615755558014, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8206fe9ee7ad7c8b9a3fd87508bf04b59d07594a443bcf683b03c260fb63a27b.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "826ecc2b935ae617fbc513c0f60647fe1f3bb40689e6b548549639025adeb681", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7f3a86e9df52b18e7703504cdc68c6f56791da668994797a0cf77617dbbe975c", "generation_seconds_batch": 18.906430852017365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26374393701553345, "target_z": -0.3222656352913521, "ce": 5.720792293548584, "genuineness": 4.3881025314331055, "identity": 0.5231223106384277, "hypothesis": "The 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_Disappointment/826ecc2b935ae617fbc513c0f60647fe1f3bb40689e6b548549639025adeb681.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "82dccfb22f0ba8ddfd360177327b1fa686de2d9199ebfd2e41a11dad928a4165", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "68f1275ee2f4ce8677740125888229d7e696381ed981a6f8dd390a1313380cfa", "generation_seconds_batch": 22.640669084037654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8349535465240479, "target_z": 0.49218751726291315, "ce": 5.871703147888184, "genuineness": 4.796044826507568, "identity": 0.5718511343002319, "hypothesis": "Die Tür ist noch offen. Ich habe einen 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_Disappointment/82dccfb22f0ba8ddfd360177327b1fa686de2d9199ebfd2e41a11dad928a4165.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "82ffa98ad534abf413b593c67d660c20769fbbc50ac5e54720d3807c642a5416", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f4770876975150987486f78e9b8607630c41a80b6b0a1bf898d325a01408fd96", "generation_seconds_batch": 14.95852147100959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3623700737953186, "target_z": -0.18164060607719135, "ce": 6.1894097328186035, "genuineness": 4.507347106933594, "identity": 0.6268119812011719, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/82ffa98ad534abf413b593c67d660c20769fbbc50ac5e54720d3807c642a5416.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "833993cb7b207aba76b32c46102b10456a3bbc47edab45a4ac9c920606da6d9c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "eef74d8cb6a64db2344efd22ccae7325ddf9f318110a2a248f12bf832811cca3", "generation_seconds_batch": 19.5196958060842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3116872012615204, "target_z": -0.2539062413685434, "ce": 6.2767791748046875, "genuineness": 4.68307638168335, "identity": 0.4645836353302002, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/833993cb7b207aba76b32c46102b10456a3bbc47edab45a4ac9c920606da6d9c.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "833ac37bb6ed3b022dbc5358f4a66f64f394ff029e8fab554510e0adce2a5b5e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a6f9ca032712bc78db9e27902ecdf481d15f5a667683f0eb85defc9737ab49e2", "generation_seconds_batch": 22.743774289032444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41442275047302246, "target_z": -0.10742185010156755, "ce": 6.046441555023193, "genuineness": 4.821148872375488, "identity": 0.7977688908576965, "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_Disappointment/833ac37bb6ed3b022dbc5358f4a66f64f394ff029e8fab554510e0adce2a5b5e.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "835ade1dfec7fa9c2709ccd85d39c2237eeac87d812f2b4566828414e48cf7c0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ef0ce62bb16179edca9193a88483314814bfb831e7ba1a5b31ccbcef80cda04e", "generation_seconds_batch": 19.316672618035227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20758184790611267, "target_z": -0.402343753319791, "ce": 5.990842819213867, "genuineness": 4.607763767242432, "identity": 0.31384551525115967, "hypothesis": "The 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_Disappointment/835ade1dfec7fa9c2709ccd85d39c2237eeac87d812f2b4566828414e48cf7c0.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "8371f937795bd8cedbca05f4824ed81d0ceed0b163c5fe05a8c6f6a6bdf4f9d4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d1f4621ced33679a431cedbf65f0e3dadcc129dbdda7349a52a3774bbd4ae352", "generation_seconds_batch": 19.399268364999443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04594460129737854, "target_z": -0.6328125039837492, "ce": 6.117925643920898, "genuineness": 4.519899368286133, "identity": 0.4330396056175232, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8371f937795bd8cedbca05f4824ed81d0ceed0b163c5fe05a8c6f6a6bdf4f9d4.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "83909d00f10b53c9fabab7131e2f47778ed21daba1b587dba89bed1a65ddfe91", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab74669cbd110975bb32b60c3815f6bf7aa6821e307c26b28d376b4052f41821", "generation_seconds_batch": 19.15581754501909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3294946849346161, "target_z": -0.2285156299796865, "ce": 6.141753673553467, "genuineness": 4.6705241203308105, "identity": 0.7509927749633789, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/83909d00f10b53c9fabab7131e2f47778ed21daba1b587dba89bed1a65ddfe91.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": "841633a913e4a275fdbf6caefb5d0808d98e06691b8ef22a2bdf6e0bcbf27141", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "31a4047797480ce60c613e42266312663fc559a99a5d73d566ba688c59c5b315", "generation_seconds_batch": 14.51111136795953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.269223153591156, "target_z": -0.31445315255426526, "ce": 5.967014789581299, "genuineness": 4.557555198669434, "identity": 0.517221212387085, "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_Disappointment/841633a913e4a275fdbf6caefb5d0808d98e06691b8ef22a2bdf6e0bcbf27141.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": "842dc0f8403a37f69852e7315966e007d130d9c5612cc55e4cdd823e78e00ab9", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8a82feb6bff147cff801df8ffa73afbfdcdf9f2d80bcbc529f1c75bbe7ea821b", "generation_seconds_batch": 19.491346533992328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25004586577415466, "target_z": -0.3417968846273939, "ce": 5.522225379943848, "genuineness": 4.595211505889893, "identity": 0.6927628517150879, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/842dc0f8403a37f69852e7315966e007d130d9c5612cc55e4cdd823e78e00ab9.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "84561e8ac448c5ce3124af9785c961f358b88a8a4bf30e808ead398db5dfaa54", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9191cfb7f4b9f47b17899048a2f414f9ed009ccc439ab56d8fbb4eeffdaa7e3a", "generation_seconds_batch": 19.449214715044945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32743996381759644, "target_z": -0.2314453322527564, "ce": 6.157639026641846, "genuineness": 4.381826400756836, "identity": 0.4596477150917053, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/84561e8ac448c5ce3124af9785c961f358b88a8a4bf30e808ead398db5dfaa54.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "846d3831572b722b461fe4b5c2fdfa56bd58ebad0e77d09ec8588599875848f1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "42fe5130abaf910fc33bac26ce5a73dc616bc67e7e3a6f919cdbc521055637c3", "generation_seconds_batch": 19.734681513975374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17470648884773254, "target_z": -0.44921873472896146, "ce": 6.292664527893066, "genuineness": 4.532451152801514, "identity": 0.7034651041030884, "hypothesis": "La porte 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_Disappointment/846d3831572b722b461fe4b5c2fdfa56bd58ebad0e77d09ec8588599875848f1.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "84bc594486ba3069ee20883dcc23cdabadef01e4788e86169db649a9745ae85a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f7fd78e2ec6689adaa900eb7581ac330f3feae78aab3a7dddbfef1a0bdac16f1", "generation_seconds_batch": 20.833634293987416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.611674964427948, "target_z": 0.1738281233401045, "ce": 5.617537498474121, "genuineness": 4.457139015197754, "identity": 0.5268247723579407, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/84bc594486ba3069ee20883dcc23cdabadef01e4788e86169db649a9745ae85a.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "84e48ae15adf414afd232e96fb20e5279bc7a7d580d06843699c2d01edebdf54", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f215d936e2d47635edc12d38188d0b8b6e7c42cb8212aa9a0b9690307df6cec7", "generation_seconds_batch": 20.01673187792767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31031739711761475, "target_z": -0.2558593620528151, "ce": 5.847874641418457, "genuineness": 4.808597087860107, "identity": 0.8357366323471069, "hypothesis": "La porte 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_Disappointment/84e48ae15adf414afd232e96fb20e5279bc7a7d580d06843699c2d01edebdf54.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "85078886358950a632dcf9675bd6c96e9d3285342662b2798cc6b6de1075c0db", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1a6275f98ba412fe3c00d975058bde400d1363fbe5090b55b8315d8b2da6d9b3", "generation_seconds_batch": 14.438800552976318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.503460168838501, "target_z": 0.01953120684271708, "ce": 6.141753673553467, "genuineness": 4.7081804275512695, "identity": 0.6166958808898926, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/85078886358950a632dcf9675bd6c96e9d3285342662b2798cc6b6de1075c0db.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "853346d9a0f78aba08367bfeb89943e303c0346d3779c10add6529abdfa06497", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7cf13e90cd8eb3e8b6d0f2a428e6313baa2d3aab7cbc22abe5bd5af879e1ecb2", "generation_seconds_batch": 19.81411392998416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17607629299163818, "target_z": -0.44726561404468973, "ce": 5.9431867599487305, "genuineness": 4.65797233581543, "identity": 0.8177509307861328, "hypothesis": "J'ai trouvé la 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_Disappointment/853346d9a0f78aba08367bfeb89943e303c0346d3779c10add6529abdfa06497.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "853bb44d932a4d81171aa189ddbbf71b5ef377599f0e57d2ebf14f32ff1d697c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "27ad80a278d0a80d936e150e66d380b78f76c35887bbf40c5f08086a5758f4b1", "generation_seconds_batch": 22.49775681993924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18292531371116638, "target_z": -0.43750001062333116, "ce": 5.903473377227783, "genuineness": 4.7081804275512695, "identity": 0.6765134334564209, "hypothesis": "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_Disappointment/853bb44d932a4d81171aa189ddbbf71b5ef377599f0e57d2ebf14f32ff1d697c.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "85509fddaa2a947a3737d00e6c9c2d218cc8a657c50cf719d7362d17f79a4fe2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a4388cea6a5fe82a8e70296df9e6e2b7b564f44b8dc19d8a977693b3f075e3e2", "generation_seconds_batch": 19.277462960919365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5883882641792297, "target_z": 0.14062502921416076, "ce": 5.6334228515625, "genuineness": 4.821148872375488, "identity": 0.6185539960861206, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/85509fddaa2a947a3737d00e6c9c2d218cc8a657c50cf719d7362d17f79a4fe2.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "856aa3c6940b33c3f883d9657e1f13712b055fb6983db85f1aa25eb04b0d5fa6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5205490e2b2d5edcfcbf1d7b9fe5ff2113950f92a448789c3fd82d57cedaa6d", "generation_seconds_batch": 19.887360075954348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2555251121520996, "target_z": -0.33398435939698234, "ce": 6.109982967376709, "genuineness": 4.758388519287109, "identity": 0.688347578048706, "hypothesis": "La porte 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_Disappointment/856aa3c6940b33c3f883d9657e1f13712b055fb6983db85f1aa25eb04b0d5fa6.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "85d854be708b106b4cdaba63960a10ffc1106dad6b6a59a5eba8d1b2b53797a8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "adbebf61a842e5ea46a9bd0e543abc94e5033afd3c9ff440c67d433c3327f305", "generation_seconds_batch": 18.965111422003247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3363437056541443, "target_z": -0.21875002655832795, "ce": 5.752562999725342, "genuineness": 4.7332844734191895, "identity": 0.7557061910629272, "hypothesis": "J'ai 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_Disappointment/85d854be708b106b4cdaba63960a10ffc1106dad6b6a59a5eba8d1b2b53797a8.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "85ef3489ccfbd2f955eee078634c42acf9ab9ad3f731448ab73b62154a116fea", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "18f7814dd5f775597d7626a86cda17e5819f3da8b547a758b0b0a5aa58b2a843", "generation_seconds_batch": 19.988078312017024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10347649455070496, "target_z": -0.5507812652710385, "ce": 6.2767791748046875, "genuineness": 4.3504462242126465, "identity": 0.29401013255119324, "hypothesis": "The 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_Disappointment/85ef3489ccfbd2f955eee078634c42acf9ab9ad3f731448ab73b62154a116fea.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "86696ddffac1aabe7b42a9926ec18efa9389f1fe6a253b79d7c94c31717aca7f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b8f55a948ea2e9511094b004eb61be3bfd151d6ed5f712d08b91ccaa2bac7220", "generation_seconds_batch": 19.388688307022676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9664549827575684, "target_z": 0.6796874428995949, "ce": 5.871703147888184, "genuineness": 4.557555198669434, "identity": 0.4766942262649536, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/86696ddffac1aabe7b42a9926ec18efa9389f1fe6a253b79d7c94c31717aca7f.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "86787bbf99a3a56fbd406eb62520e963e15251d87957d05e55c66baca3fec2c5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bf0e16b4c562dbd1074dafbaac5f3521852874bff8f266374b22ed8b908505b8", "generation_seconds_batch": 19.067818469018675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5185281038284302, "target_z": 0.04101566184968004, "ce": 5.847874641418457, "genuineness": 4.758388519287109, "identity": 0.8252121210098267, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/86787bbf99a3a56fbd406eb62520e963e15251d87957d05e55c66baca3fec2c5.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "86ed024dc958fabd1efb367796e33d6f53cac0e81e3c86e577e014a2bccdb6a9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8b713e482f0e628367f2564d13b16212e7802e7b505ce96766d38eb366c9414b", "generation_seconds_batch": 14.47174917603843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24319683015346527, "target_z": -0.35156250929541477, "ce": 6.173524379730225, "genuineness": 4.846253395080566, "identity": 0.620147168636322, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/86ed024dc958fabd1efb367796e33d6f53cac0e81e3c86e577e014a2bccdb6a9.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "86fd0e1028b3b127ad2cb8f3571bbbdcb4c26c981cfafd5e4e1987010a39205f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1fe313d8a4cacf6e4632ff95766aea3ef4de0c73dadc103caa815c3059017698", "generation_seconds_batch": 23.32112313003745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17196685075759888, "target_z": -0.45312501859082954, "ce": 5.879645347595215, "genuineness": 4.369274139404297, "identity": 0.4834411144256592, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/86fd0e1028b3b127ad2cb8f3571bbbdcb4c26c981cfafd5e4e1987010a39205f.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "874459f2be1d75e88d85e65455be6fd70137e61a1f799eef834a0a11325dcaa1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "369b1df5417cf1905f63cde2c494a9bf0a2e6d234ce361d43dbf068201e4a82a", "generation_seconds_batch": 19.30622890300583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24182702600955963, "target_z": -0.3535156299796865, "ce": 5.692992687225342, "genuineness": 4.720732688903809, "identity": 0.641099214553833, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/874459f2be1d75e88d85e65455be6fd70137e61a1f799eef834a0a11325dcaa1.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "87b7720f7713cf5e4f3470cc938ba327e5c8884fac30a09ec627da64325c26f2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a195241155244b4fcfa4f1e47b92a08119058c4f754c48e97ea18eab2d4cacbd", "generation_seconds_batch": 19.123856881051324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24593645334243774, "target_z": -0.347656246680209, "ce": 5.911416053771973, "genuineness": 4.6203155517578125, "identity": 0.5197129249572754, "hypothesis": "La porte 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_Disappointment/87b7720f7713cf5e4f3470cc938ba327e5c8884fac30a09ec627da64325c26f2.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "883faf0afc6a4a1c5c1adf1e80bf3e4339fe204be33e4af59b5f2238d8602aa0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5124dc337f7933aa7c983902f048779fd01c6f8132623d0a4e28d37363957be8", "generation_seconds_batch": 14.95852147100959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25689488649368286, "target_z": -0.33203128120603537, "ce": 6.054384231567383, "genuineness": 4.545003414154053, "identity": 0.42132076621055603, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/883faf0afc6a4a1c5c1adf1e80bf3e4339fe204be33e4af59b5f2238d8602aa0.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "88e6dbf04db4b66fe96d23ff825160b63e0499c5dc4a9622429622c06bc2bb4c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "530543d5a82050d7fced1acbfd7bbfc3db293ab213b59c0b8e45b57139ae6de2", "generation_seconds_batch": 19.085748651996255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6637276411056519, "target_z": 0.2480468793157283, "ce": 6.006728172302246, "genuineness": 4.607763767242432, "identity": 0.6734722852706909, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/88e6dbf04db4b66fe96d23ff825160b63e0499c5dc4a9622429622c06bc2bb4c.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": "894e35703dd52ece69b47ecf771f5d841732b3339329217d9f4954f1ca74f79c", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da3ff3ff49d53441a04bee6acff3d6aa8e7b6919992e1a92d4d11b33043d2385", "generation_seconds_batch": 14.809686066000722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5089394450187683, "target_z": 0.027343774566453354, "ce": 5.637393951416016, "genuineness": 4.607763767242432, "identity": 0.586362361907959, "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_Disappointment/894e35703dd52ece69b47ecf771f5d841732b3339329217d9f4954f1ca74f79c.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": "89c34924bec7d02d95126da274f975ee3668ed6b4c09fefb723d4c058043cd07", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c02ff67edfb077787e7e6af3edea8d223dea6eb67b6a8437ac9b0e830582917c", "generation_seconds_batch": 14.564329573069699, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40620389580726624, "target_z": -0.11914061670052252, "ce": 5.927301406860352, "genuineness": 4.770940780639648, "identity": 0.5525856614112854, "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_Disappointment/89c34924bec7d02d95126da274f975ee3668ed6b4c09fefb723d4c058043cd07.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "8a41fd71bdcf404d32577917d449820a8ba31eedd4b4370081237b9fde77b216", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "790ad087a8e08fbe61e2532bc11a4f2c38afa4662cd01ff852f70488ebff16df", "generation_seconds_batch": 14.346919521107338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1336122751235962, "target_z": -0.5078124827370868, "ce": 5.919358730316162, "genuineness": 4.808597087860107, "identity": 0.5102816820144653, "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_Disappointment/8a41fd71bdcf404d32577917d449820a8ba31eedd4b4370081237b9fde77b216.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": "8a8aa1f5a856df0b70dd67551dba8d26252c64efdf6fd9d1a72985fc06f5a11b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "10ef03f90474ebcde04c9a13b8031c191c6d7045bac289cabc9e8104699ef6b5", "generation_seconds_batch": 14.58777686196845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.632906973361969, "target_z": 0.20410155768630306, "ce": 5.597680568695068, "genuineness": 4.457139015197754, "identity": 0.6748253703117371, "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_Disappointment/8a8aa1f5a856df0b70dd67551dba8d26252c64efdf6fd9d1a72985fc06f5a11b.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "8a9228b0c800902774cdee040866cf0ce201087d87964b6d55c203a14e22e0cc", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0b871ff6572dc6b0d712ee5ec462dd478b5da9d3be79fb60845a179d2cf67588", "generation_seconds_batch": 19.30819051002618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38154736161231995, "target_z": -0.1542968740040627, "ce": 5.919358730316162, "genuineness": 4.507347106933594, "identity": 0.19583213329315186, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8a9228b0c800902774cdee040866cf0ce201087d87964b6d55c203a14e22e0cc.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "8ad765488c8eff0946c8dbeb297f0bbfc37d26e7c698f4dec35803d09bc04fb9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "71f18189035544febb2649f0234c4d9dcfdf16a72f8ab5a011857dd8bd180942", "generation_seconds_batch": 16.76668018696364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4692150354385376, "target_z": -0.02929685275740034, "ce": 5.645336627960205, "genuineness": 4.6705241203308105, "identity": 0.531243085861206, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8ad765488c8eff0946c8dbeb297f0bbfc37d26e7c698f4dec35803d09bc04fb9.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "8ba4b4c7bfbd77772540d8d7296fc788d57d42e718ded8b178b9f5ec0f2b39eb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f9ee667746fdcb4ef7d9becd59715d6b2b2a98a6dc9a3394279073874cb07da1", "generation_seconds_batch": 14.197549600969069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16374802589416504, "target_z": -0.46484374269645984, "ce": 5.911416053771973, "genuineness": 4.758388519287109, "identity": 0.4514957070350647, "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_Disappointment/8ba4b4c7bfbd77772540d8d7296fc788d57d42e718ded8b178b9f5ec0f2b39eb.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "8bbc2fe64371c38aeebbf77868e33db34408d9c98b6cfabeebeefac5c27cc7f9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2df8583005e3f6c592eb2c51babfedcd535dacd2c3a9f50c4cc13f844fc2e02", "generation_seconds_batch": 19.006341258995235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 5.959072113037109, "genuineness": 4.545003414154053, "identity": 0.3757936656475067, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8bbc2fe64371c38aeebbf77868e33db34408d9c98b6cfabeebeefac5c27cc7f9.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "8bc20badb2f5f065586d78e6314fd09620b8fddf7bfbb7ba478dd28a03aeefe5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "65dd8da0613db7a029ee1264ffca27f9aeb2186e3b6b326c0092c21959a90f2b", "generation_seconds_batch": 19.8159930909751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22127991914749146, "target_z": -0.3828125039837492, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.573736846446991, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8bc20badb2f5f065586d78e6314fd09620b8fddf7bfbb7ba478dd28a03aeefe5.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": "8bd1e292ec988f5390a053dccd266298b3a6af2f39b8a7d986f4ac431f4f7493", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "924ce6152400117fabfcc5170a251a273984e5c019585aa7606a705b6d429000", "generation_seconds_batch": 14.431711748009548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1979931890964508, "target_z": -0.41601564060301766, "ce": 6.0146708488464355, "genuineness": 4.6705241203308105, "identity": 0.5635759830474854, "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_Disappointment/8bd1e292ec988f5390a053dccd266298b3a6af2f39b8a7d986f4ac431f4f7493.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "8cb457374b9902b46746a742f93e623f11d3aeedd44314856078eb247214a55b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87f0c914bc9c0e7dfa4be8d387c43b9a45c03aebbf3acfacb4239d0d601c7502", "generation_seconds_batch": 19.317675288999453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0239869356155396, "target_z": 0.761718766598955, "ce": 5.728734970092773, "genuineness": 4.2249250411987305, "identity": 0.49675896763801575, "hypothesis": "Ik heb het kleine doosje gevonden. Dat 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_Disappointment/8cb457374b9902b46746a742f93e623f11d3aeedd44314856078eb247214a55b.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "8d115fc5e6a8a9b8f0a7a4c36e2ff436fcf267507b9248e85091e47d95aceba4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "14c1e1ec3328ff52d9f787da542aa82fb8fa8d46e4e0044560d0bbde93841627", "generation_seconds_batch": 19.29861100600101, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23908740282058716, "target_z": -0.35742189259489227, "ce": 6.1020402908325195, "genuineness": 4.632867813110352, "identity": 0.7558035254478455, "hypothesis": "La porte 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_Disappointment/8d115fc5e6a8a9b8f0a7a4c36e2ff436fcf267507b9248e85091e47d95aceba4.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "8db484dcc047c5387abd0f9fed311965fde6ffc6384de376e7dca0ce05c1ca1a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d478a55b4e38d54bdfb004354e8c43ae762be97f5d1450409e5db0e752f220a", "generation_seconds_batch": 19.137558708083816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3870266079902649, "target_z": -0.14648434877365116, "ce": 5.6334228515625, "genuineness": 4.971774101257324, "identity": 0.7211827635765076, "hypothesis": "La porte 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_Disappointment/8db484dcc047c5387abd0f9fed311965fde6ffc6384de376e7dca0ce05c1ca1a.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "8dd728035bd99de699bf4af00dfec5716a019b4f29910dec6638a6c43bfb308f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9fa3382111c6cd273a605613b8b2e88fbb132520451b66074300b926e28e6ea4", "generation_seconds_batch": 19.318088673055172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04320499300956726, "target_z": -0.6367187453522926, "ce": 6.483288764953613, "genuineness": 4.595211505889893, "identity": 0.43586909770965576, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8dd728035bd99de699bf4af00dfec5716a019b4f29910dec6638a6c43bfb308f.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "8e24d7d24742efb7999a717f295abe32fb41452a151ba75f91bfb6ddc9c2106e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f24008f58d275b21f617ab506f8675331c765d754bac169b172b9ca018603705", "generation_seconds_batch": 20.166732070967555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0979972779750824, "target_z": -0.5585937480081254, "ce": 6.308549880981445, "genuineness": 4.645420074462891, "identity": 0.5588949918746948, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8e24d7d24742efb7999a717f295abe32fb41452a151ba75f91bfb6ddc9c2106e.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "8e39734986ab41ed990db7118df7d651e85b442e54ec7a98e548a6bb53be22e6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "41f5fc3264c02fd6a2cb01b1525dcbc8bcd57ea36a8f4eae12aba7e6bef2bbcb", "generation_seconds_batch": 19.09152650204487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3651096820831299, "target_z": -0.17773436470864792, "ce": 5.903473377227783, "genuineness": 4.6705241203308105, "identity": 0.527962327003479, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8e39734986ab41ed990db7118df7d651e85b442e54ec7a98e548a6bb53be22e6.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "8e85bf8a9764f1e1f18b9f788195eb43a41a86ac158fe2f6e6a061e820922260", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4de93ee169b3fa747d43a5bdd4f8ab2748b7d04e9cb3f257f65d491ed4b8a10a", "generation_seconds_batch": 19.159893534961157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.889745831489563, "target_z": 0.5703125146070803, "ce": 5.998785495758057, "genuineness": 4.344170093536377, "identity": 0.631655752658844, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8e85bf8a9764f1e1f18b9f788195eb43a41a86ac158fe2f6e6a061e820922260.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "8ecf0f3a37103138630f0cb1682368a7090b895c8789c6e84fbda93b9a6ffe80", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "71e44a396064b76ae656cc75c2c38eea27b79375df82c4099ff30cb0cc7add49", "generation_seconds_batch": 21.37852370494511, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10621613264083862, "target_z": -0.5468749814091705, "ce": 6.205295085906982, "genuineness": 4.381826400756836, "identity": 0.4142506718635559, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8ecf0f3a37103138630f0cb1682368a7090b895c8789c6e84fbda93b9a6ffe80.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "8f781bb68979858050b6cec185eb2d99124011c210fa529aace747624f5d372b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd18ff41d3525a443947691fe13d91ee3563c47228eb3695a63d6d196d17b39f", "generation_seconds_batch": 14.220688870060258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3610002398490906, "target_z": -0.18359376925478776, "ce": 5.458683967590332, "genuineness": 4.15588903427124, "identity": 0.20068608224391937, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8f781bb68979858050b6cec185eb2d99124011c210fa529aace747624f5d372b.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "8fc4b9a9e442813225d95424500f7d29ac99e560c95bd73e93853083569afec3", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9a804ed693ada58904cf48ead45a67951b26cb1c75028c172a5b87293279eba7", "generation_seconds_batch": 22.046711196075194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10073688626289368, "target_z": -0.554687506639582, "ce": 6.09409761428833, "genuineness": 4.369274139404297, "identity": 0.6936863660812378, "hypothesis": "J'ai trouvé la 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_Disappointment/8fc4b9a9e442813225d95424500f7d29ac99e560c95bd73e93853083569afec3.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "8ffb39993000d93293b22c7b342d447b1221f2626970278236d02cc944b93dba", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5ec15ce28614bfe9ef94b98679fa5def3e96b2bf800d41fef551a08b1c89fc72", "generation_seconds_batch": 19.366665142937563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4089435040950775, "target_z": -0.1152343753319791, "ce": 5.569881439208984, "genuineness": 4.607763767242432, "identity": 0.48450660705566406, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/8ffb39993000d93293b22c7b342d447b1221f2626970278236d02cc944b93dba.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "9064d85600a44f3fc6ac02e87c3015022022f0e709b0cf8d70203ac4ac0b87f1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3865689a3aa76f87564cfd6bbb8572cf815756f9e107891f17cb1275628e2bd0", "generation_seconds_batch": 19.433488579001278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12265381217002869, "target_z": -0.5234374907045852, "ce": 6.268836498260498, "genuineness": 4.68307638168335, "identity": 0.6476116180419922, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9064d85600a44f3fc6ac02e87c3015022022f0e709b0cf8d70203ac4ac0b87f1.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "90f17ca207a23fdd618aafeb3db1cfdeddbf258a6ef5f7c4b4b9e67a04a99e60", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "49fda39ff6794e3c33bda611ec49a46afbf89abb8a6fee32c91459aacbf15371", "generation_seconds_batch": 22.800505244988017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16785743832588196, "target_z": -0.45898438064364466, "ce": 6.062326908111572, "genuineness": 4.482243061065674, "identity": 0.49807828664779663, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/90f17ca207a23fdd618aafeb3db1cfdeddbf258a6ef5f7c4b4b9e67a04a99e60.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "90f6cd4a6e8e05b8dfd71023d11da4fcbf199a0388bdc48c3e1c5c8b74121b98", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "538d4aadc8355c7443882b0cdead2fbb620a184fbde3e56160a8752846f468ce", "generation_seconds_batch": 19.050823209923692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1692272424697876, "target_z": -0.457031259959373, "ce": 5.824047088623047, "genuineness": 4.68307638168335, "identity": 0.6706088185310364, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/90f6cd4a6e8e05b8dfd71023d11da4fcbf199a0388bdc48c3e1c5c8b74121b98.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "90ff43fd913b9552aebac73acc430a1e808517d1ce0d1137813c6b4c4a0413a6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5a8faf92414b15c664e5af86f3884540273e4c5e244747c85ba3eff19215e9c2", "generation_seconds_batch": 19.19308620505035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49181684851646423, "target_z": 0.0029297022730699236, "ce": 5.903473377227783, "genuineness": 4.419482707977295, "identity": 0.5241824984550476, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/90ff43fd913b9552aebac73acc430a1e808517d1ce0d1137813c6b4c4a0413a6.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "9110bcc7743234b50306f30b8f719b07ce43bed8df5b4921b93d5348991893f9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0c9c883f0a2ff17bbe2a2530d9ea4baf4e9f80e025bc786dc4d459073f7883be", "generation_seconds_batch": 22.17689439491369, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30346834659576416, "target_z": -0.2656250079674984, "ce": 5.824047088623047, "genuineness": 4.557555198669434, "identity": 0.3059312403202057, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9110bcc7743234b50306f30b8f719b07ce43bed8df5b4921b93d5348991893f9.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "9152211b5262a52d3646247c2017663ba5268ab6ccfcd503c926563d5d151b8e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b5e26ba7148256b1db959e1274695367e4a388fdffddfb07578873bc7f8bdd8a", "generation_seconds_batch": 20.290116627933457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6205787062644958, "target_z": 0.18652342903453298, "ce": 6.078212261199951, "genuineness": 4.381826400756836, "identity": 0.47200867533683777, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9152211b5262a52d3646247c2017663ba5268ab6ccfcd503c926563d5d151b8e.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": "917de923b8647d4db8aa861c140d67bad387f1f314822f01b40c06ab5a87cb8f", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9920e365ca56de37d9a15d6ea9d80bdceb3a39290a4fc4280a0a1791a3b2fbc0", "generation_seconds_batch": 19.26732879295014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8650892972946167, "target_z": 0.5351562573035402, "ce": 5.7406487464904785, "genuineness": 4.482243061065674, "identity": 0.1276543289422989, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik los het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/917de923b8647d4db8aa861c140d67bad387f1f314822f01b40c06ab5a87cb8f.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "91f454dd471d9aea17aacd74e151451b883f8c4c2535bd762803894e0ca54094", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7f8c7ea72051569bfc67f93eb45d0cf5eef872cee4aafe2069b1197a69a4c784", "generation_seconds_batch": 19.442223489051685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6815351247787476, "target_z": 0.27343749070458523, "ce": 5.804190158843994, "genuineness": 4.432034492492676, "identity": 0.26013004779815674, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/91f454dd471d9aea17aacd74e151451b883f8c4c2535bd762803894e0ca54094.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": "92eb2ba953ae258e86b34062c1173420d835c2a1cbf473f4d52d6a46fe7c5edc", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7e7797fe27f0b579201d7c575238096564804c611ee79eeb89af0db414e5d864", "generation_seconds_batch": 15.236456067999825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7554638385772705, "target_z": 1.804687336666283, "ce": 5.967014789581299, "genuineness": 4.406930446624756, "identity": 0.3673180043697357, "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_Disappointment/92eb2ba953ae258e86b34062c1173420d835c2a1cbf473f4d52d6a46fe7c5edc.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": "933907e4be81df3c47fd4b4ebd71e85196cc9993a53c5e68a6e2b578cf8ba2d4", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61e2cb669416c0801a6ab2b12eb0a42458cbabd9ddb6fe5c4176beabb6839ddc", "generation_seconds_batch": 19.26732879295014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1719260215759277, "target_z": 0.9726561404468972, "ce": 5.903473377227783, "genuineness": 4.68307638168335, "identity": 0.22648561000823975, "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_Disappointment/933907e4be81df3c47fd4b4ebd71e85196cc9993a53c5e68a6e2b578cf8ba2d4.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "9379e61ff6fdcdfc580f877d956aff31fb939175a91fe8b5ae029cea0b8db75e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e48155ac0dca0b8db9c49b2440c07584bd678c10313be1fde048bec813de1de", "generation_seconds_batch": 14.550586065044627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29250991344451904, "target_z": -0.2812499734416721, "ce": 6.173524379730225, "genuineness": 4.871357440948486, "identity": 0.7812680006027222, "hypothesis": "Ma porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9379e61ff6fdcdfc580f877d956aff31fb939175a91fe8b5ae029cea0b8db75e.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "93cd4176eb49922a96e8b547584b4ea741c5be53bbbf4b03256e48fa84d142e1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a52c37c1d7856989f5e7a46dc62375f54bf30feaaa32c1c8f0c9961f71a890f8", "generation_seconds_batch": 19.070308316964656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2829212546348572, "target_z": -0.29492186072489873, "ce": 5.95112943649292, "genuineness": 4.821148872375488, "identity": 0.6455672383308411, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/93cd4176eb49922a96e8b547584b4ea741c5be53bbbf4b03256e48fa84d142e1.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "941780c93663f254da9e51a2685e455792d39683ed67e3b4b5775ff82637c26a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f6cba4c39b7fb54f5923ada664e743915d6d1b24ce127464185679fd32475d15", "generation_seconds_batch": 21.021900134976022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07060113549232483, "target_z": -0.597656246680209, "ce": 6.213237762451172, "genuineness": 4.68307638168335, "identity": 0.43533676862716675, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/941780c93663f254da9e51a2685e455792d39683ed67e3b4b5775ff82637c26a.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "941b36fbe30ce50603820b8aed56a02725fb81586760470a4f6e45be778323dc", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3bf57d93fbb72e828cc99d080b4927e0f64db71f7d5adf815eef9bb47612b168", "generation_seconds_batch": 19.99589622602798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07334074378013611, "target_z": -0.5937500053116656, "ce": 6.292664527893066, "genuineness": 4.68307638168335, "identity": 0.6099344491958618, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie standen neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/941b36fbe30ce50603820b8aed56a02725fb81586760470a4f6e45be778323dc.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "941ec07bc2c1f6a607660cba9ca5c986ce50d4029ad554689a87c7eaed949bc5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0371ed2405065dcd0ddeb4dfd7bb59eb63b21f87b687837c7777cdf75f3e81b6", "generation_seconds_batch": 14.242542922031134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2870306670665741, "target_z": -0.2890624986720836, "ce": 6.0305562019348145, "genuineness": 4.883909225463867, "identity": 0.5335395336151123, "hypothesis": "La porte 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_Disappointment/941ec07bc2c1f6a607660cba9ca5c986ce50d4029ad554689a87c7eaed949bc5.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "94b765f9b66a3a193c81e9419aea0f0903a99b32e3b8dc22e4e50cfd509c78ce", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "460ed70a9b07e78d01212d804b98491dc66388aa44e0c42211bb01fe4becea10", "generation_seconds_batch": 14.392381074023433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7020822167396545, "target_z": 0.3027343434619856, "ce": 5.824047088623047, "genuineness": 4.413206577301025, "identity": 0.6788488626480103, "hypothesis": "Ik 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_Disappointment/94b765f9b66a3a193c81e9419aea0f0903a99b32e3b8dc22e4e50cfd509c78ce.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "94fd7fa847a22f97f6545ac359766bbab5f2ae71b41d235f62581af70fb4c633", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "21691422cefccafd00b54a5be468036e2b8aa05006bb99576c4d609ee7d4c33c", "generation_seconds_batch": 15.595077709993348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26100432872772217, "target_z": -0.3261718766598955, "ce": 5.601652145385742, "genuineness": 4.607763767242432, "identity": 0.8107402324676514, "hypothesis": "J'ai trouvé la 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_Disappointment/94fd7fa847a22f97f6545ac359766bbab5f2ae71b41d235f62581af70fb4c633.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "9501de3c58562b634132493b019c093e26a8ca79e4264b029aba4c821bcdb91d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c942027e08aca1b8d731fee15b543015090e007da2b2a5d3f607c4ba1460fd0c", "generation_seconds_batch": 18.98531072505284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06786152720451355, "target_z": -0.6015624880487525, "ce": 5.919358730316162, "genuineness": 4.432034492492676, "identity": 0.2384430319070816, "hypothesis": "The 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_Disappointment/9501de3c58562b634132493b019c093e26a8ca79e4264b029aba4c821bcdb91d.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "953ad8dd9bce85ee2f690255179465c005a8d5bc4d162ea7193105a878098a59", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a16823dce4e7bfe25351cd8c10fce6f3f2a5645bf6c3d7b28a5e8cd4224526b3", "generation_seconds_batch": 14.929536634939723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5151035785675049, "target_z": 0.036132838892338405, "ce": 6.086154937744141, "genuineness": 4.344170093536377, "identity": 0.6982930302619934, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/953ad8dd9bce85ee2f690255179465c005a8d5bc4d162ea7193105a878098a59.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": "9561165862004a5024adcde405722a7373a2e47418a5503476ccc41884e50bc8", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c0863c6424b09f4659f8534415f936b47039d4fdfd74df9ae140b477a989fd0f", "generation_seconds_batch": 14.41395164001733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33908334374427795, "target_z": -0.2148437426964598, "ce": 5.474569320678711, "genuineness": 4.65797233581543, "identity": 0.6925616264343262, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9561165862004a5024adcde405722a7373a2e47418a5503476ccc41884e50bc8.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "9657824f92ba366d4dad2b9426956e6ab8165f6b529c0f907d14eb190a702604", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b98d19b9f54000bdba73426b5992b5b0d5bade285ced75ddc62d6bd7fc50203e", "generation_seconds_batch": 19.076112948008813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0130283832550049, "target_z": 0.7460936311514824, "ce": 5.661221981048584, "genuineness": 4.406930446624756, "identity": 0.31239065527915955, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9657824f92ba366d4dad2b9426956e6ab8165f6b529c0f907d14eb190a702604.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "965d7d2d1cd10550e40beb95772e32b44b0259146a2afd1172cc1e99802e1801", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "24616d4467e2f4d6ab953f421cac58691dddb0583f97d98d25e0636411c2c009", "generation_seconds_batch": 19.173974264995195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15689897537231445, "target_z": -0.4746093886111431, "ce": 6.022613525390625, "genuineness": 4.720732688903809, "identity": 0.7880046367645264, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/965d7d2d1cd10550e40beb95772e32b44b0259146a2afd1172cc1e99802e1801.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "96e442ab6c0d1fed36e851216a57a5f803d935ee5e4454d6469052fc80b71058", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "07055c0c8315fbf9e6d96060d01bb54b8def0b11a941547516ce5caf876a6d98", "generation_seconds_batch": 19.44540380698163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6226334571838379, "target_z": 0.1894531738009276, "ce": 5.403085231781006, "genuineness": 4.632867813110352, "identity": 0.5332432985305786, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/96e442ab6c0d1fed36e851216a57a5f803d935ee5e4454d6469052fc80b71058.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "96ecd4ec8c90204a730bd612d3dd70e6b614d5654c503366b9deddfbc95ba04e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "663bc3b44f890873171b9cbc91931cb3e526e37089a73d541a409818f3efa356", "generation_seconds_batch": 23.47681622894015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.026726484298706, "target_z": 0.7656249229808489, "ce": 6.109982967376709, "genuineness": 4.7332844734191895, "identity": 0.6162396669387817, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/96ecd4ec8c90204a730bd612d3dd70e6b614d5654c503366b9deddfbc95ba04e.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "9770e1f64e1f9de7b204a7ba48351edfbf9b8a99db55dd253cee17acdcda07fd", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "14e93b8a7995ab7653fb21c2fdb3fec571756bb0f05320e577ac8bece026e7a2", "generation_seconds_batch": 19.60932068096008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6048259139060974, "target_z": 0.16406247742542124, "ce": 5.831989288330078, "genuineness": 4.545003414154053, "identity": 0.5848559141159058, "hypothesis": "De deur 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_Disappointment/9770e1f64e1f9de7b204a7ba48351edfbf9b8a99db55dd253cee17acdcda07fd.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "979922966f44329a766c5699ad1c5f99d0dc2ff578b9be59973845c9968a2412", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "278b1185bfb7c030a56cae49d5d86af46bb4baa4d4136c3e4ce32cfb52e3726a", "generation_seconds_batch": 22.70355949900113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7459160685539246, "target_z": 0.3652343753319791, "ce": 5.744620323181152, "genuineness": 4.356721878051758, "identity": 0.35406744480133057, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/979922966f44329a766c5699ad1c5f99d0dc2ff578b9be59973845c9968a2412.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "97b35fc6d4b58c68347a95cbbffe3867314af5a8d6ce4c6aefc64003bd3135b7", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ce5bdbbf61fd59217f2ede39cae0a7a776a1626b4c47ac48bb31d846e7336355", "generation_seconds_batch": 15.694644161965698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14594054222106934, "target_z": -0.49023435408531674, "ce": 6.054384231567383, "genuineness": 4.65797233581543, "identity": 0.6856971979141235, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/97b35fc6d4b58c68347a95cbbffe3867314af5a8d6ce4c6aefc64003bd3135b7.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "98487c9b6e52dbe480defded6147c265a27d6f7da673c88aef7179525408bfba", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c856d41a6fbc1f5515c8267b059abfadaed06ac2d9fe62d660ebdb3c7f7d0820", "generation_seconds_batch": 19.078102680039592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7239991426467896, "target_z": 0.33398435939698234, "ce": 6.070269584655762, "genuineness": 4.444586753845215, "identity": 0.4406198263168335, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/98487c9b6e52dbe480defded6147c265a27d6f7da673c88aef7179525408bfba.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "98cb28806d1509b23156ab15c7453ad6da5f1ae07a90644e8134c9eacc865031", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a5237a443b462faf1ccdb63643da9310a2391b35034c5096b8705e60720a20af", "generation_seconds_batch": 19.102543856948614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.377437949180603, "target_z": -0.16015623605687782, "ce": 6.157639026641846, "genuineness": 4.846253395080566, "identity": 0.2732943594455719, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/98cb28806d1509b23156ab15c7453ad6da5f1ae07a90644e8134c9eacc865031.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "98f66ed7b7bac664c0eb3974e33990a3ca57da9ac914c85c4456b71a01533c15", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5eca4733a19d046f06b7ed4398a019a1e07efd44cf4e9432f27c8f108e14960c", "generation_seconds_batch": 19.99589622602798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002110779285430908, "target_z": -0.695312493360418, "ce": 6.316492557525635, "genuineness": 4.369274139404297, "identity": 0.5967519879341125, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/98f66ed7b7bac664c0eb3974e33990a3ca57da9ac914c85c4456b71a01533c15.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "9912b553fd4a9dcbd876d20338dc33ad60aedca22670c1b4e64caf5922149016", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0498604f679dae55774ffc17ed3a2925ec3c61168296c7cec50d215863af171a", "generation_seconds_batch": 19.227872506016865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23634779453277588, "target_z": -0.36132813396343566, "ce": 5.804190158843994, "genuineness": 4.7458367347717285, "identity": 0.7750939726829529, "hypothesis": "La porte 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_Disappointment/9912b553fd4a9dcbd876d20338dc33ad60aedca22670c1b4e64caf5922149016.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "999aa3f3052747fa8b21a2bf3be0c06db1ef3a51b5dcb167e4bc4d2960a03647", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ba69b5eb08449bc64e19c6d93a48961203b15f21b4d7b9214b1ad2e4c9e3c8ee", "generation_seconds_batch": 19.222120622056536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.051423847675323486, "target_z": -0.6249999787533377, "ce": 6.109982967376709, "genuineness": 4.432034492492676, "identity": 0.7617665529251099, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/999aa3f3052747fa8b21a2bf3be0c06db1ef3a51b5dcb167e4bc4d2960a03647.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "01f34b6b72e8da256187a2136429318d067815e7a2fc1144055e56971fc2b60f", "generation_seconds_batch": 14.962605006992817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17607629299163818, "target_z": -0.44726561404468973, "ce": 6.308549880981445, "genuineness": 4.632867813110352, "identity": 0.419217973947525, "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_Disappointment/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.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": "9af4d7b396a107aaca3ff55bc2dafa566f1c344b2f1bc1fed3b724f62b5e5954", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c219afbe23a2c528dcf213387533ed62a89fc3f5e6f7c172b1876fced464bf5", "generation_seconds_batch": 15.125061876955442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42401137948036194, "target_z": -0.0937500053116656, "ce": 5.8875885009765625, "genuineness": 4.218649387359619, "identity": 0.45847952365875244, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9af4d7b396a107aaca3ff55bc2dafa566f1c344b2f1bc1fed3b724f62b5e5954.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "9b2fc38d11a606bb660fd75d6c04202716a9817f992ce25c3c9acbe5a8bc2dab", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2fc4bda784f68ab1e113107a6342d33da5f0df03acc2cdb3de4fd85d2f56c083", "generation_seconds_batch": 19.207481314078905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0623414516448975, "target_z": 0.8164061457585627, "ce": 6.268836498260498, "genuineness": 4.532451152801514, "identity": 0.5511874556541443, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9b2fc38d11a606bb660fd75d6c04202716a9817f992ce25c3c9acbe5a8bc2dab.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "64c8a663636177102d2d71f51d301414045b2ab3ad706081a10aad8573f78930", "generation_seconds_batch": 17.060368397040293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11717456579208374, "target_z": -0.5312500159349968, "ce": 6.260893821716309, "genuineness": 4.20609712600708, "identity": 0.7218655347824097, "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_Disappointment/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "9c512fe265a84b074741725d387b9aa7f9792d682ac37afc6b34df029aa77616", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bbe04fa4b0d3bcab80c956284eb1c9071c16388cae5231b59a0bd92737818fb6", "generation_seconds_batch": 19.30622890300583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7513952851295471, "target_z": 0.37304685806906596, "ce": 5.760505676269531, "genuineness": 4.632867813110352, "identity": 0.6376229524612427, "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_Disappointment/9c512fe265a84b074741725d387b9aa7f9792d682ac37afc6b34df029aa77616.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "18fd85f5e7ab1094e28b4fd453fbccdc37c11fe8197f1605dff5c7ce7e316f4a", "generation_seconds_batch": 16.38664360693656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18977436423301697, "target_z": -0.4277343647086479, "ce": 6.133810997009277, "genuineness": 4.243753433227539, "identity": 0.49564433097839355, "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_Disappointment/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.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": "9cdd331fd287727b61c29d97b2095ae1df145fbcc1e74864760d91b66549ccea", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f4277fe6d376fc925c5dc95cf79c333de394c46809586d00aa80493772cd34e1", "generation_seconds_batch": 15.236456067999825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5198571681976318, "target_z": 1.4687500690516526, "ce": 5.871703147888184, "genuineness": 4.381826400756836, "identity": 0.1598663181066513, "hypothesis": "Uw bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9cdd331fd287727b61c29d97b2095ae1df145fbcc1e74864760d91b66549ccea.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "9d40551fa07f18bb4282c8b5d30e0a54a23444a1e5f29e41f0ab62f5c7939189", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "faafa7f6cb9acc80ce889b65fb46b4d7f8cef48ea73ea33a7f3c3b6f27cb48d1", "generation_seconds_batch": 19.77028188307304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44592830538749695, "target_z": -0.06249998937666882, "ce": 5.80021858215332, "genuineness": 4.375550270080566, "identity": 0.39528971910476685, "hypothesis": "De deur staat nog open. Ik heb je jas op je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9d40551fa07f18bb4282c8b5d30e0a54a23444a1e5f29e41f0ab62f5c7939189.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "9d656d6a946f5f3c36b76f915264233b76c66deda4f1c4ac7ba0351dec1a240d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "96a916c066eef8b4ff25e2d372f14a91c943e1a5eb13792f8cf5bf16f2381235", "generation_seconds_batch": 20.01456618902739, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5952372550964355, "target_z": 0.15039059014219455, "ce": 6.1020402908325195, "genuineness": 4.256305694580078, "identity": 0.49384963512420654, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9d656d6a946f5f3c36b76f915264233b76c66deda4f1c4ac7ba0351dec1a240d.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "9eadbbed421b45893e0e76ac550837b373a181212cd7542cec1e2eda01f2c928", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c14f899e7f2fbc00f4ab2b914257fa000e984ebe5f839e913a1fd9428c97bcca", "generation_seconds_batch": 19.388031775015406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2555251121520996, "target_z": -0.33398435939698234, "ce": 6.221180438995361, "genuineness": 4.6203155517578125, "identity": 0.4512680768966675, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/9eadbbed421b45893e0e76ac550837b373a181212cd7542cec1e2eda01f2c928.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": "a06032038777784a4569e670408a5ae767b2ee847662ef3bc830cf79d98016b8", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c1705c2667a7b62d854e74b5a0279608ee0a17572f124f6b6348bc6c128d61c9", "generation_seconds_batch": 14.431711748009548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5198978781700134, "target_z": 0.04296874004062702, "ce": 5.855817794799805, "genuineness": 4.68307638168335, "identity": 0.5820097327232361, "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_Disappointment/a06032038777784a4569e670408a5ae767b2ee847662ef3bc830cf79d98016b8.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "a0606359ef422972b0cb6d069a43cb7f02898871ff7f58fc4a4fdfdc292fce59", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd7cbb73ec38c33d1d0d44c24531d0fbcb58250922bb3660476a1c30c8718984", "generation_seconds_batch": 19.078102680039592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.569210946559906, "target_z": 0.11328125464770739, "ce": 5.871703147888184, "genuineness": 4.344170093536377, "identity": 0.6152705550193787, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a0606359ef422972b0cb6d069a43cb7f02898871ff7f58fc4a4fdfdc292fce59.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "a06cae0f042b546de2db0c482a647e41164adeaa8d464fcb3277cebfa93af116", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "556d1a6c8669f71cc2a24273f8cb533eb7071b534fe2f8460f1c53155532e17d", "generation_seconds_batch": 19.222120622056536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10073688626289368, "target_z": -0.554687506639582, "ce": 6.038498878479004, "genuineness": 4.632867813110352, "identity": 0.6737264394760132, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a06cae0f042b546de2db0c482a647e41164adeaa8d464fcb3277cebfa93af116.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": "a0d4ae959507e598e75e878cad6442cab730663d408746e47bbeaf3a8f0a412a", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fbd6f2166da7db6c767b15a36854ff4bb9cc8f56a6e79dec3de65b55998d1f3e", "generation_seconds_batch": 14.378284808946773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30757778882980347, "target_z": -0.2597656034213585, "ce": 5.824047088623047, "genuineness": 4.231201171875, "identity": 0.5625013113021851, "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_Disappointment/a0d4ae959507e598e75e878cad6442cab730663d408746e47bbeaf3a8f0a412a.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": "a0fd529c7f49bcc44ad7277a2d88b1ab0df7a4f17e12df24876efc37b9a43202", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b64a5eb41bfaf4b429088ca82a12727e718f3b2e4dcbb7f78a9cc9d77a2a9be", "generation_seconds_batch": 15.537088027922437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.269223153591156, "target_z": -0.31445315255426526, "ce": 5.998785495758057, "genuineness": 4.6705241203308105, "identity": 0.4513022005558014, "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_Disappointment/a0fd529c7f49bcc44ad7277a2d88b1ab0df7a4f17e12df24876efc37b9a43202.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "a105337bcfbdf0472a45a367d514cbb089f70d667bdaa5f1caa62a8a545863cc", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3c82fdd68fb259a1fe105647f613187be855af6ec8a3c8aabc1fdc904a071059", "generation_seconds_batch": 21.5864803600125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2979891300201416, "target_z": -0.27343749070458523, "ce": 6.149696350097656, "genuineness": 4.909013748168945, "identity": 0.5601983666419983, "hypothesis": "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_Disappointment/a105337bcfbdf0472a45a367d514cbb089f70d667bdaa5f1caa62a8a545863cc.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "a11ed9add4cfa35b967fcc2a9265875711fcc8d77dbaae4b8f8992671b55cc1e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bbcf665e1aa08b45bb88222ff3e36947cd3b52348b3b39225cc6c0865a432a90", "generation_seconds_batch": 19.207859067013487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44181889295578003, "target_z": -0.06835935142948395, "ce": 6.117925643920898, "genuineness": 4.758388519287109, "identity": 0.7823693752288818, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a11ed9add4cfa35b967fcc2a9265875711fcc8d77dbaae4b8f8992671b55cc1e.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "a139cb24cf4c042669de225029887a237be301efe66701b3117a713b0e1f8a89", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "75db1019061c85dbbfd762db8fe093b1620a331e92fda32971a66e6ad74a2be8", "generation_seconds_batch": 19.459415694931522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08155959844589233, "target_z": -0.5820312387127107, "ce": 6.046441555023193, "genuineness": 4.632867813110352, "identity": 0.809539794921875, "hypothesis": "J'ai trouvé la 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_Disappointment/a139cb24cf4c042669de225029887a237be301efe66701b3117a713b0e1f8a89.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "a14a06b96426f253c764a68c489bdd0db0aa826ab6dd17b456dedee3f50ab941", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "282bc937f5f0c91a0628ccf539562a3d84f87322e39213842c84dcdab23af6c8", "generation_seconds_batch": 20.971131057012826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2651137709617615, "target_z": -0.32031247211375563, "ce": 5.9431867599487305, "genuineness": 4.65797233581543, "identity": 0.7993676662445068, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a14a06b96426f253c764a68c489bdd0db0aa826ab6dd17b456dedee3f50ab941.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "a190255096ba900dba8be11780eeac72ba63e235c6b8f7e0b0c972f896be6bb0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a79a53d609c7ad4ccacb6ea54483c04296d0d1db7ad311981841182bae370189", "generation_seconds_batch": 19.270680351066403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13635188341140747, "target_z": -0.5039062413685435, "ce": 6.062326908111572, "genuineness": 4.720732688903809, "identity": 0.8191834688186646, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a190255096ba900dba8be11780eeac72ba63e235c6b8f7e0b0c972f896be6bb0.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": "a1ac113845c4698e37815fdd6e6dd8eee0b4cd19b97400547314cb1d2d2bbc0b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b2ed08cff73c0a4b7636b0586a3895d87e0efad0b97bcb8c2e66f051a94c9cf7", "generation_seconds_batch": 19.376421839930117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7445462942123413, "target_z": 0.36328129714103213, "ce": 5.788304805755615, "genuineness": 4.293961524963379, "identity": 0.22485148906707764, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a1ac113845c4698e37815fdd6e6dd8eee0b4cd19b97400547314cb1d2d2bbc0b.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "a27b5efcf385ccd22adb083f8424ab4ecf42a7bed9e80387f11fbc6b3bf7f360", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2d72500e032ef7203d475b818a04562d0cba37b5a6c9c0a6c852e29ace0509f2", "generation_seconds_batch": 19.21610655693803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16785743832588196, "target_z": -0.45898438064364466, "ce": 6.197352409362793, "genuineness": 4.532451152801514, "identity": 0.37599560618400574, "hypothesis": "The 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_Disappointment/a27b5efcf385ccd22adb083f8424ab4ecf42a7bed9e80387f11fbc6b3bf7f360.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "a2abe238ccd96208ea549f9a6a07c73ee1b6acead325e4cbe43294a3a0f3615c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3d01d81cbd7bb639063d977b7a0da625a7fc6735f7da7dd0b72f9f0c7afea64d", "generation_seconds_batch": 20.266036090091802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1555291712284088, "target_z": -0.47656250929541477, "ce": 5.708878040313721, "genuineness": 4.6203155517578125, "identity": 0.5771226286888123, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a2abe238ccd96208ea549f9a6a07c73ee1b6acead325e4cbe43294a3a0f3615c.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "a2fc01cd000c415fa804f225c496298bff1517b284734575794c6e63d63fa1f3", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc31049ca8349cace3e9fbd61a619bcbbfd4f172d2c12cea618a92eed30c2461", "generation_seconds_batch": 19.03942416398786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28840047121047974, "target_z": -0.2871093779878119, "ce": 5.2045183181762695, "genuineness": 4.645420074462891, "identity": 0.7356868982315063, "hypothesis": "La porte 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_Disappointment/a2fc01cd000c415fa804f225c496298bff1517b284734575794c6e63d63fa1f3.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "a34323670bba5f82f2ad680fbb376237905b79fdb6eabd8dc952c0959350a022", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bf38c6bf5ebb924c463090023782bf83fe58fc201f15d2947955952376e64457", "generation_seconds_batch": 14.222704694024287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6219485402107239, "target_z": 0.1884765922121294, "ce": 5.561938762664795, "genuineness": 4.645420074462891, "identity": 0.44889217615127563, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a34323670bba5f82f2ad680fbb376237905b79fdb6eabd8dc952c0959350a022.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "a38d440a1db4c5d985b4b0c9f1ba97294626b39fd646675dcb22b4f49951f949", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d882f3643a0b6e3a1798e5b3022184ca3a2bd42b4a3deea9fcb558f9636a8a5a", "generation_seconds_batch": 19.207859067013487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3692190945148468, "target_z": -0.1718750026558328, "ce": 5.982900142669678, "genuineness": 4.7081804275512695, "identity": 0.8503022193908691, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a38d440a1db4c5d985b4b0c9f1ba97294626b39fd646675dcb22b4f49951f949.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "a39c53e1dbbd9724c4adfd9157c3ba2a215b60fc4bcd8563411a598cdadc2b33", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8c5bfde6cd3c2c0637abaa370b27e5162ee50abdb957cdb7e75bf2b17d1b88bf", "generation_seconds_batch": 19.13074116304051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17607629299163818, "target_z": -0.44726561404468973, "ce": 5.816103935241699, "genuineness": 4.883909225463867, "identity": 0.6411157846450806, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a39c53e1dbbd9724c4adfd9157c3ba2a215b60fc4bcd8563411a598cdadc2b33.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": "a3ae8618ce37de79e3f8514367862a252a2f1b3a5bbbf5de65e44663685e7ac4", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "207694f52a2e6fefd5db8e3de9cc28b0c48bfbb37311709a746e28031e7d30d6", "generation_seconds_batch": 14.641394773032516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9938511848449707, "target_z": 0.718750026558328, "ce": 5.613565921783447, "genuineness": 4.65797233581543, "identity": 0.7323797345161438, "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_Disappointment/a3ae8618ce37de79e3f8514367862a252a2f1b3a5bbbf5de65e44663685e7ac4.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "a3c689f2f64d2b535abace1f943554291202047d0589d5d5e3cde2ec503091af", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4185cbf1d8ceabc9441fed2d56e5fa59764497006d8144e15114f7b2ea4d1c4a", "generation_seconds_batch": 16.77847273997031, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1089557409286499, "target_z": -0.542968740040627, "ce": 6.173524379730225, "genuineness": 4.871357440948486, "identity": 0.7755321264266968, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a3c689f2f64d2b535abace1f943554291202047d0589d5d5e3cde2ec503091af.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": "a411d43f4cb92332cfcdcc3f34c9e472608487a4efe537af9876854dc60b6ca8", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "659f05dffaaeb1a503ae51809b45445828004d1685957b38291fc30b71f15356", "generation_seconds_batch": 14.472820817958564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33086448907852173, "target_z": -0.22656250929541477, "ce": 5.597680568695068, "genuineness": 4.3881025314331055, "identity": 0.27424266934394836, "hypothesis": "De weg gaat linksaf naar de brug, loopt verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a411d43f4cb92332cfcdcc3f34c9e472608487a4efe537af9876854dc60b6ca8.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "a417b2c5d2e407c4c74e88eae9ec6fb1a6d860fc9bca58ec3059ce7f84323e95", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "870538fc4d7c229118d5b8190f99d38709f559d25db28a3286e9f7ce9dee625b", "generation_seconds_batch": 14.043995323008858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19662338495254517, "target_z": -0.4179687612872894, "ce": 6.157639026641846, "genuineness": 4.482243061065674, "identity": 0.25733307003974915, "hypothesis": "The 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_Disappointment/a417b2c5d2e407c4c74e88eae9ec6fb1a6d860fc9bca58ec3059ce7f84323e95.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "a43f3bb6af6348b4235df26cc48dd5a45b3e8387c02df1ab85cdcc5e3d552cef", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4ddeacfb0b76f35bd9b420cb0a6abd46a298ffa8c846052126a928b19646bea7", "generation_seconds_batch": 14.322613025084138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.568526029586792, "target_z": 0.11230467305890918, "ce": 5.903473377227783, "genuineness": 4.293961524963379, "identity": 0.6001193523406982, "hypothesis": "Ik 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_Disappointment/a43f3bb6af6348b4235df26cc48dd5a45b3e8387c02df1ab85cdcc5e3d552cef.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "a44ccfd6b5903c6f42f4b663666af908f05984fcc0c929fd193445ceb745ec61", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5bc5df1190b780f4ff4d93101fdadc7e8889b931d9dbefd4ef28a55814b31b63", "generation_seconds_batch": 14.237055195029825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24593645334243774, "target_z": -0.347656246680209, "ce": 5.708878040313721, "genuineness": 4.770940780639648, "identity": 0.5837567448616028, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a44ccfd6b5903c6f42f4b663666af908f05984fcc0c929fd193445ceb745ec61.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "a47e718af1464858671e7a98c57b80476ce84fedb06df3fcccbbd36bdaf6db08", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "48b51918016917e843929124112ac52db1839ba3145174a2173cf799756478f5", "generation_seconds_batch": 14.940915031940676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08429920673370361, "target_z": -0.5781249973441672, "ce": 6.252951145172119, "genuineness": 4.65797233581543, "identity": 0.671654224395752, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a47e718af1464858671e7a98c57b80476ce84fedb06df3fcccbbd36bdaf6db08.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "a52a943447d300e61108fb5fb58748c38f80ea883153cdcc2c8f47ef059e8d69", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9ba8029817a547bffa1a7ace4aa7a53ed27fa71d74e7dd5719484e5fe2d07c38", "generation_seconds_batch": 21.729358191019855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19251397252082825, "target_z": -0.4238281233401045, "ce": 5.990842819213867, "genuineness": 4.519899368286133, "identity": 0.42120426893234253, "hypothesis": "The 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_Disappointment/a52a943447d300e61108fb5fb58748c38f80ea883153cdcc2c8f47ef059e8d69.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "a587685270d0d94370e863839b2cb9c0e0d509034748f77f1999632f8031417e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1540cc1673a20e874a91c3ce988740547c1460de20cdd0f135fd3c1177975954", "generation_seconds_batch": 22.50045674503781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11717456579208374, "target_z": -0.5312500159349968, "ce": 6.300607204437256, "genuineness": 4.545003414154053, "identity": 0.4434639811515808, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a587685270d0d94370e863839b2cb9c0e0d509034748f77f1999632f8031417e.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "a5b916627a680b209de070496f4a94f5870400a2b588bf2475a8d5b920d9d711", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "241ea75d70f819f203f8ca34d6ba72ec0f833809ca0ba80df216a6f64f567083", "generation_seconds_batch": 20.204713333048858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2979891300201416, "target_z": -0.27343749070458523, "ce": 5.387199878692627, "genuineness": 4.557555198669434, "identity": 0.41646909713745117, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a5b916627a680b209de070496f4a94f5870400a2b588bf2475a8d5b920d9d711.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": "a5bc0b0a5e3bad7f6bcacbf10f22dc3b329545871f37989403c91ef784c35849", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0f8018ec07ed4e4e3ee516d231f01533213421027182f585e9c312b5941c7f1d", "generation_seconds_batch": 14.482510081026703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22127991914749146, "target_z": -0.3828125039837492, "ce": 5.5738525390625, "genuineness": 4.582659721374512, "identity": 0.7922396659851074, "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_Disappointment/a5bc0b0a5e3bad7f6bcacbf10f22dc3b329545871f37989403c91ef784c35849.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "a5c85146aeb559f854f839744111a393535a0c337e97b2b787ee5d038054cc1a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "99e365f7b684a1f9613e38d7d5476cf79f04d1976e78aa2abbaf0805803a2504", "generation_seconds_batch": 14.245066997944377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23634779453277588, "target_z": -0.36132813396343566, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.49616485834121704, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a5c85146aeb559f854f839744111a393535a0c337e97b2b787ee5d038054cc1a.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "a5d3d76b7fc11abf59ea3f9e61ab87e335ee5a2b514ddf342857aae8fe9a912a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0c7a954a7f4e6afba7dde923d3f9540cb6e6018c0c853d715bb76418018f00dd", "generation_seconds_batch": 19.366665142937563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5116790533065796, "target_z": 0.031250015934996773, "ce": 5.585766792297363, "genuineness": 4.582659721374512, "identity": 0.6416560411453247, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a5d3d76b7fc11abf59ea3f9e61ab87e335ee5a2b514ddf342857aae8fe9a912a.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "a64f0d387003f8b7638d633132adcf69abd26c9cc546ecca196cd7a156e03a6d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e21cd23b0a68333f2fd2d30b4f642dced514b8ed6b09a93f74de9573cfa83b0b", "generation_seconds_batch": 19.604396044043824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24867606163024902, "target_z": -0.3437500053116656, "ce": 5.8875885009765625, "genuineness": 4.519899368286133, "identity": 0.5799123048782349, "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_Disappointment/a64f0d387003f8b7638d633132adcf69abd26c9cc546ecca196cd7a156e03a6d.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "a653019c12f008e9a009babc67c6e0bcbd8e226197aa7eb9768d72d43cb99d89", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1951a06f194dfd87a0d2decd0039eb08cbea0da8886a68100e5cb217f85f7bd5", "generation_seconds_batch": 19.116253744112328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9144023656845093, "target_z": 0.6054687719106205, "ce": 5.871703147888184, "genuineness": 4.406930446624756, "identity": 0.5214000344276428, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a653019c12f008e9a009babc67c6e0bcbd8e226197aa7eb9768d72d43cb99d89.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": "a67f343c56a0fa3eb759d27bd57c43a5e3a9784ce01686c4304bf37eaa20a8a9", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a907a40f4bc037952e4a2c2580e5c8c1679e079e4c368b10c23e4253e8db5949", "generation_seconds_batch": 14.52662561100442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23908740282058716, "target_z": -0.35742189259489227, "ce": 5.816103935241699, "genuineness": 4.65797233581543, "identity": 0.6312446594238281, "hypothesis": "Las llaves están en la mesa de la cocina. Mire en el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a67f343c56a0fa3eb759d27bd57c43a5e3a9784ce01686c4304bf37eaa20a8a9.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": "a6daf48bb6be99c2ba2ab8cc574345bd25c8495bc7155c68a21574a0dfbaac39", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f379285a4b520819218b4c5cd58803391467a3c094dcfd39f304c213e3e1bc7", "generation_seconds_batch": 19.69398797105532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2336081862449646, "target_z": -0.3652343753319791, "ce": 6.316492557525635, "genuineness": 4.68307638168335, "identity": 0.44092023372650146, "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_Disappointment/a6daf48bb6be99c2ba2ab8cc574345bd25c8495bc7155c68a21574a0dfbaac39.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": "a6e7018694a404196223b02cef7a9a6191c03f69a8d06628ff2df48513ce855e", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51650d8a394c526e2529e285b9b9864e3d220077cacd3cccc11dea486c201efb", "generation_seconds_batch": 19.48368712689262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20347243547439575, "target_z": -0.4082031153726061, "ce": 5.998785495758057, "genuineness": 4.821148872375488, "identity": 0.7927757501602173, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a6e7018694a404196223b02cef7a9a6191c03f69a8d06628ff2df48513ce855e.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "a746011d72ec098009815ef90ef2ddec24fafd381f25d122c999d00bb1f061ba", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "80cb4d4167a1b3a74d727b4fbf2ef1984bb371657c7ce0922e6ae0a1545c8e0e", "generation_seconds_batch": 19.17863205401227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8144063949584961, "target_z": 0.46289057951886337, "ce": 5.637393951416016, "genuineness": 4.507347106933594, "identity": 0.545885443687439, "hypothesis": "De de deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a746011d72ec098009815ef90ef2ddec24fafd381f25d122c999d00bb1f061ba.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "a764416f8dcd24e8f82fc03858e821be3e18b14457f1a19a896c442e534e69b2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6c000bfbdca37acc41851fdb715e1fbd3b925dbd0d480385afe89f47c2166a84", "generation_seconds_batch": 15.046090407064185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30346834659576416, "target_z": -0.2656250079674984, "ce": 5.990842819213867, "genuineness": 4.570107460021973, "identity": 0.6345266699790955, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a764416f8dcd24e8f82fc03858e821be3e18b14457f1a19a896c442e534e69b2.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "a776c9e87d26072808ef91d728069d6fd44a9598dfddff157fee8be86fa519a5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "95510b4aa6fb5999df30898bd21eb3e846672023d039d6e3b66dc9409355e53d", "generation_seconds_batch": 14.395342324045487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1979931890964508, "target_z": -0.41601564060301766, "ce": 6.165581703186035, "genuineness": 4.18099308013916, "identity": 0.44743072986602783, "hypothesis": "The 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_Disappointment/a776c9e87d26072808ef91d728069d6fd44a9598dfddff157fee8be86fa519a5.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "a807c47c735c2a4565511aefbdb25a920d4e65c60a32a0faef2ab93133a01f0a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "36f6e51c9653a64be001a218affc2502db8c92aab14426bdd8c7c952ea7e57b0", "generation_seconds_batch": 20.622409850009717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41442275047302246, "target_z": -0.10742185010156755, "ce": 5.744620323181152, "genuineness": 4.7834930419921875, "identity": 0.6261520385742188, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a807c47c735c2a4565511aefbdb25a920d4e65c60a32a0faef2ab93133a01f0a.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "a81d6bb5a7202edfa8621839cfa925ad910c9e2d82ef34502931ca1cd43e266d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "67b9a93ab053788e038ac8c72946ccee0704d3badff09319d59b7c9219dba6a4", "generation_seconds_batch": 19.339680974022485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22812896966934204, "target_z": -0.37304685806906596, "ce": 5.982900142669678, "genuineness": 4.532451152801514, "identity": 0.719030499458313, "hypothesis": "La porte 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_Disappointment/a81d6bb5a7202edfa8621839cfa925ad910c9e2d82ef34502931ca1cd43e266d.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "96f6d6bd717f48ed20eeeb6bd450c4c5457caabc39dc9eba9fce8a1e2b41f0ed", "generation_seconds_batch": 16.317306171054952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10621613264083862, "target_z": -0.5468749814091705, "ce": 6.070269584655762, "genuineness": 4.293961524963379, "identity": 0.6964633464813232, "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_Disappointment/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "a8df8fd217b90b648cfe9d552216d5dcc6ff2103ee3fa9a401212ddd14c9bfac", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4fec6586a51628fef6ebf17c5ce07adb769788a8635af26abb9ef4d17bdd5c35", "generation_seconds_batch": 20.30152127891779, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09525766968727112, "target_z": -0.5624999893766688, "ce": 6.197352409362793, "genuineness": 4.7081804275512695, "identity": 0.6825100183486938, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a8df8fd217b90b648cfe9d552216d5dcc6ff2103ee3fa9a401212ddd14c9bfac.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "a91cae07cde2599ae1bc2287a3355a8f582f94e08eb0e9dbad2de71ee76442b2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2070e80d8b03a98fc7eb2ec65cefa13d2da8f85377af2a5c7cb1a540a531e1f5", "generation_seconds_batch": 21.89223956502974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 5.7128496170043945, "genuineness": 4.68307638168335, "identity": 0.3663631081581116, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a91cae07cde2599ae1bc2287a3355a8f582f94e08eb0e9dbad2de71ee76442b2.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "a9a26eba95d155e78a07fea460035d4700f06f000b3d410bcd31e41e8cc41b09", "generation_seconds_batch": 14.609102912945673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3363437056541443, "target_z": -0.21875002655832795, "ce": 6.046441555023193, "genuineness": 4.344170093536377, "identity": 0.5700023174285889, "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_Disappointment/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "a99a428a6dabd76bd706a0623b32eac9dd5e528674b3481bf323ddad025bf972", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d1d3a0060e9f737ebf35c298c72fa3b7b193e3a860ff31fddfd3c978be6e79c6", "generation_seconds_batch": 19.181637019035406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32401543855667114, "target_z": -0.23632815521009803, "ce": 5.470598220825195, "genuineness": 4.833701133728027, "identity": 0.6540044546127319, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/a99a428a6dabd76bd706a0623b32eac9dd5e528674b3481bf323ddad025bf972.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "aa834869c1653bda7f9a9ccd590a15181aaa27d64c8ea2b4a8fefbe063028617", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e208505990ac03a3a599fa1df4b9f04191993ff7ba711de58eeade9c21c6dd27", "generation_seconds_batch": 19.77028188307304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6137296557426453, "target_z": 0.17675778311984972, "ce": 6.006728172302246, "genuineness": 4.519899368286133, "identity": 0.5083067417144775, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/aa834869c1653bda7f9a9ccd590a15181aaa27d64c8ea2b4a8fefbe063028617.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": "aab60eff1f0ccdc8f231797e4b0e0058fe95f543781c03941f3f5caf09563705", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b79a9ca809a1993f44d70a500ca4917250b5bd1db925942da732030e02a08a5", "generation_seconds_batch": 14.474110077950172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4185321629047394, "target_z": -0.10156248804875243, "ce": 5.426913261413574, "genuineness": 4.482243061065674, "identity": 0.4622504711151123, "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_Disappointment/aab60eff1f0ccdc8f231797e4b0e0058fe95f543781c03941f3f5caf09563705.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d607dbb51b882c719c9f5f049afbeca1b9eb21607c7427f87ef7096eec1600e4", "generation_seconds_batch": 14.309465100988746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21032145619392395, "target_z": -0.3984375119512476, "ce": 6.507116317749023, "genuineness": 4.13078498840332, "identity": 0.4634372591972351, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.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": "ac3b83d03c750b3343e0a4c16205f943e85157625691bdc6187a6000d1542bc9", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fd31e2d0a7e98d1965be3e889304a9fbf725ff04972f9b8978b320ec5918bec7", "generation_seconds_batch": 19.30290964397136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22949877381324768, "target_z": -0.37109373738479423, "ce": 5.863759994506836, "genuineness": 4.808597087860107, "identity": 0.7590128183364868, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ac3b83d03c750b3343e0a4c16205f943e85157625691bdc6187a6000d1542bc9.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "ac72c6eca04f5f6a4a421c96d0643e738f3e5524a9874accd9fb6de8dd172b13", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "80a08c92b9b788097d4aa790cf70db5b1f583d08d02eb36b5905c55a5ba9ad56", "generation_seconds_batch": 15.901431978098117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2158007025718689, "target_z": -0.390624986720836, "ce": 6.086154937744141, "genuineness": 4.532451152801514, "identity": 0.7739918828010559, "hypothesis": "La porte 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_Disappointment/ac72c6eca04f5f6a4a421c96d0643e738f3e5524a9874accd9fb6de8dd172b13.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "acee1891b59c5418af29f32cca7766d6d74ae393e62a73a6e508e86096db4f18", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2697bd0ae4b1d0a37879dd2e01d21c25ea0f642f828a133807ff90928063e182", "generation_seconds_batch": 16.912312091095373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2979891300201416, "target_z": -0.27343749070458523, "ce": 6.078212261199951, "genuineness": 4.8588056564331055, "identity": 0.809363067150116, "hypothesis": "La porte est encore ouverte J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt, fromiters.", "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_Disappointment/acee1891b59c5418af29f32cca7766d6d74ae393e62a73a6e508e86096db4f18.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "ad00672edbda3603e89029bd95da3e630047f546f41be8a9df50a3aba796ad78", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "163d10fccb687e616ef4a31865d42bf7024be7bc10e11dfcb31f6c31badad0d7", "generation_seconds_batch": 21.244034571922384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4870225191116333, "target_z": -0.0039062413685434154, "ce": 5.764476776123047, "genuineness": 4.369274139404297, "identity": 0.5123659372329712, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ad00672edbda3603e89029bd95da3e630047f546f41be8a9df50a3aba796ad78.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "ad103d3ea568f22dafa63481daf3f714a3ed86bac45ec645a89d6f608bf94cec", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "18137e0afa4ab48a2ea7dc8739b24fbd198105eb73710565db2bceaf2f7ac789", "generation_seconds_batch": 14.799304928979836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17607629299163818, "target_z": -0.44726561404468973, "ce": 6.054384231567383, "genuineness": 4.808597087860107, "identity": 0.7378020286560059, "hypothesis": "J'ai trouvé la 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_Disappointment/ad103d3ea568f22dafa63481daf3f714a3ed86bac45ec645a89d6f608bf94cec.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "ad3049740cec4e067ba5ec2b0a5dc4506260adf4cee0e0dbab2f71384c15f5c2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "31156029ab5482dfd9d39ffcc178ced6b918403f6f56f48d1801a7e89a0072cc", "generation_seconds_batch": 19.21523822005838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5520883798599243, "target_z": 0.08886722484764868, "ce": 5.577824115753174, "genuineness": 4.7458367347717285, "identity": 0.6206244230270386, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ad3049740cec4e067ba5ec2b0a5dc4506260adf4cee0e0dbab2f71384c15f5c2.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "ad628687c2ed2b4d603bdaf0fc283372bece9e14117c12d67477c9862a0c0da9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ef6eeef1d53717fda237cb37f5c46086218a3d664cef9f153e4d6cbe0febcb2c", "generation_seconds_batch": 19.510900696041062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2089516520500183, "target_z": -0.4003906326355193, "ce": 6.356205940246582, "genuineness": 4.394378662109375, "identity": 0.44948819279670715, "hypothesis": "The 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_Disappointment/ad628687c2ed2b4d603bdaf0fc283372bece9e14117c12d67477c9862a0c0da9.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "2e26aaa6f9235d02ee5ac5d6073d38e8216d7220b27681b689b9f1643be25851", "generation_seconds_batch": 18.707228335086256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6061957478523254, "target_z": 0.16601564060301768, "ce": 6.125868320465088, "genuineness": 4.293961524963379, "identity": 0.7966949343681335, "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_Disappointment/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "adfb1e8cd4a3e2e442d6138614ff8fa64a560e0eb2253254cc529ccea3a14554", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a48354a1b319bf5328b4a43febbd03f36d97ad91b6afa92bda037977b2b9c790", "generation_seconds_batch": 14.220688870060258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0869979858398438, "target_z": 0.851562403062103, "ce": 5.593709468841553, "genuineness": 4.293961524963379, "identity": 0.3924958109855652, "hypothesis": "De deur staat nog open. Ik heb je 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_Disappointment/adfb1e8cd4a3e2e442d6138614ff8fa64a560e0eb2253254cc529ccea3a14554.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "51f5342de515c5287decde22abbda6470e78677ed8343bc063e42acf77508051", "generation_seconds_batch": 14.307214510045014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2021026313304901, "target_z": -0.41015623605687784, "ce": 6.324435234069824, "genuineness": 4.036643981933594, "identity": 0.06393474340438843, "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_Disappointment/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "ae6dc06ed6deb6cfdea883336231305d15124d48e915dd4d80469bdc1255d4e9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "105cbe9916d1dd626d3cfed34644f06490715a9d499c00584e363cff0e301471", "generation_seconds_batch": 19.433488579001278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.062382280826568604, "target_z": -0.609375013279164, "ce": 6.300607204437256, "genuineness": 4.68307638168335, "identity": 0.6027724742889404, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ae6dc06ed6deb6cfdea883336231305d15124d48e915dd4d80469bdc1255d4e9.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "af75bc82e3bf58ee63bcd47cd5ef14fc762beab8526c0b3f36f282e1d49d6e59", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "426db280c690c843171a65ce82a114484d58f445201467a8b2ababe2dfd6b49d", "generation_seconds_batch": 19.5196958060842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1801857054233551, "target_z": -0.4414062519918746, "ce": 6.221180438995361, "genuineness": 4.545003414154053, "identity": 0.4523194432258606, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/af75bc82e3bf58ee63bcd47cd5ef14fc762beab8526c0b3f36f282e1d49d6e59.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "af790e6925c4784495642cfdf7584c5cf1138ed02715297ea9d733611f6406ad", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d1789b74cf5e67167b2e87f26e06eb324e1a8d9cf19996602f1fa01b9c8793a0", "generation_seconds_batch": 19.043710296973586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2158007025718689, "target_z": -0.390624986720836, "ce": 5.542081832885742, "genuineness": 4.645420074462891, "identity": 0.49698567390441895, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/af790e6925c4784495642cfdf7584c5cf1138ed02715297ea9d733611f6406ad.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "afe2c8994b82dc5be82de8513bbe1ac7e80787d7d78fef566118f26591c68b1a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "678d3c7352988f6de7725e51b22df82799a81781f68c9b51ef17a3b6accd7e66", "generation_seconds_batch": 14.159526592935435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6664672493934631, "target_z": 0.2519531206842717, "ce": 6.157639026641846, "genuineness": 4.7332844734191895, "identity": 0.7071354389190674, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/afe2c8994b82dc5be82de8513bbe1ac7e80787d7d78fef566118f26591c68b1a.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "afeaa4c68616570d913ca51bcb0ba1ce31e43387a030d059ffc6307be67247f7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "51c17ce16267e913b7f69d00d56eb9c6f65117ba90e407bf653421d514a326d0", "generation_seconds_batch": 19.007845676969737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2582647204399109, "target_z": -0.3300781180284389, "ce": 6.038498878479004, "genuineness": 4.632867813110352, "identity": 0.5819133520126343, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/afeaa4c68616570d913ca51bcb0ba1ce31e43387a030d059ffc6307be67247f7.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "b0073df9c0838a10df58d5355abc35f3544ed7e16fe4d9d46fc06f89869f96a7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "95e95ee848a167fa434b293e881cbb6282f396761838bdc578ba5e06bae1a0ac", "generation_seconds_batch": 20.266036090091802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14731034636497498, "target_z": -0.488281233401045, "ce": 6.221180438995361, "genuineness": 4.808597087860107, "identity": 0.5194295048713684, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b0073df9c0838a10df58d5355abc35f3544ed7e16fe4d9d46fc06f89869f96a7.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "b017356dab34a773165c43e11c4363a9f474495c052ab033b2c0269b05d43aa4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75e39013fc61f0edae19da15f482063ecedfe021037cef5967224903c65b1fe4", "generation_seconds_batch": 20.94831195799634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24730625748634338, "target_z": -0.3457031259959373, "ce": 6.062326908111572, "genuineness": 4.7332844734191895, "identity": 0.7747849225997925, "hypothesis": "La porte 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_Disappointment/b017356dab34a773165c43e11c4363a9f474495c052ab033b2c0269b05d43aa4.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "b0345681a1babc7e73be411b8bda0c04eecd4534a4f3579dde925d6da6da916c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "eff18f6b3a7635fd0ac8245d83aa2b2c384814a52ddacb6809c85b8d705886cc", "generation_seconds_batch": 14.327234541997313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28840047121047974, "target_z": -0.2871093779878119, "ce": 6.165581703186035, "genuineness": 4.821148872375488, "identity": 0.7714174389839172, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b0345681a1babc7e73be411b8bda0c04eecd4534a4f3579dde925d6da6da916c.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "b0c46e438b150c240c58831ee0faee39c2168bde6d74610ac4419245becc0642", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "964a72e430f99efc434db5406acb267d2b85cc1165a38ef5016a4330ea8d45e7", "generation_seconds_batch": 22.048881554976106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18292531371116638, "target_z": -0.43750001062333116, "ce": 5.371314525604248, "genuineness": 4.645420074462891, "identity": 0.5490984916687012, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b0c46e438b150c240c58831ee0faee39c2168bde6d74610ac4419245becc0642.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "b11dc4f5600363174530b6694f1b95c0299ec69acc74716293e829d4cfcf2dbe", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d948ea45b2bf92bb5d79729fa9508b4f3dd5170050de818e7e7310373eb10320", "generation_seconds_batch": 19.302563984063454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8349535465240479, "target_z": 0.49218751726291315, "ce": 5.982900142669678, "genuineness": 4.444586753845215, "identity": 0.47586560249328613, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b11dc4f5600363174530b6694f1b95c0299ec69acc74716293e829d4cfcf2dbe.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "b2099fc4889d1b47d4ebefbe76ed26b92bdc31bba2459aba706433aa0ce2f7df", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4923a4a2ad842101a81c55ab8c9898b4ad9061911a01bd7b2d41ac212636b277", "generation_seconds_batch": 19.105153116979636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22949877381324768, "target_z": -0.37109373738479423, "ce": 5.804190158843994, "genuineness": 4.331617832183838, "identity": 0.44153663516044617, "hypothesis": "The 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_Disappointment/b2099fc4889d1b47d4ebefbe76ed26b92bdc31bba2459aba706433aa0ce2f7df.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "b20dd222a09ccfa8a8c20489ab504f3bf596f33824b496e725fdf3296be22e45", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ebcc88fba5699589123d8c7ebcd492c55e0d11b587a0d067f611a38644775b4d", "generation_seconds_batch": 20.959235907997936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21717050671577454, "target_z": -0.38867186603656434, "ce": 5.919358730316162, "genuineness": 4.758388519287109, "identity": 0.6866350173950195, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b20dd222a09ccfa8a8c20489ab504f3bf596f33824b496e725fdf3296be22e45.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "b2abc1a3c94409cbdd958f77d3912b5136ebc0bb948252bcbfe00676bea55ccb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d7d73a6a4b90bb54a49add315c98ee8d516e70d05aea04213fb7b6cec5935fb9", "generation_seconds_batch": 19.76903395401314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5390751957893372, "target_z": 0.07031251460708038, "ce": 6.086154937744141, "genuineness": 4.645420074462891, "identity": 0.5132611989974976, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b2abc1a3c94409cbdd958f77d3912b5136ebc0bb948252bcbfe00676bea55ccb.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "b2f3a704c44d556d1d01cc38c7a6ce17103f28a8d1cd20e83afd746767b23369", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "95229426294fbb9ae6231f7b19bc0eca6e028a62021b5e992bf612177c6c0dcc", "generation_seconds_batch": 15.410941771930084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12265381217002869, "target_z": -0.5234374907045852, "ce": 6.181467056274414, "genuineness": 4.174716949462891, "identity": 0.4248164892196655, "hypothesis": "The 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_Disappointment/b2f3a704c44d556d1d01cc38c7a6ce17103f28a8d1cd20e83afd746767b23369.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "b378da262325f5d8d319a75e95d7c1cac8385201a9b08bb0eab6f2086e010225", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d97efe0930accd196afbd8edbc142034452ccef94a1e0964726fa4e9dbb82385", "generation_seconds_batch": 15.046090407064185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2664835453033447, "target_z": -0.31835939392280865, "ce": 6.23706579208374, "genuineness": 4.68307638168335, "identity": 0.6065405011177063, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b378da262325f5d8d319a75e95d7c1cac8385201a9b08bb0eab6f2086e010225.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "b422dee1b1ba1aa1d6d6f564c5d6728b75e6ba29c828146f733dbc7a7a6c1668", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0e11bb83d43dfdd77d34bb439b09df0a25bd3e0e10175cde9609bb1544ff23f", "generation_seconds_batch": 14.15129143500235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26785337924957275, "target_z": -0.31640623074521224, "ce": 5.998785495758057, "genuineness": 4.7458367347717285, "identity": 0.7754597067832947, "hypothesis": "De la porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b422dee1b1ba1aa1d6d6f564c5d6728b75e6ba29c828146f733dbc7a7a6c1668.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "36641641df009ab873e0242c3b0a1c3b70fd22fd1459caea9e6d4c70bc573afd", "generation_seconds_batch": 15.907562467968091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23086857795715332, "target_z": -0.3691406167005225, "ce": 6.316492557525635, "genuineness": 4.7081804275512695, "identity": 0.6296401023864746, "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_Disappointment/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "b44324f527d4327161f1929621ba07c3109d871760d1739fba230ff5eaabafe9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "017653c4b24dbcaa78425d75fcb92036ffaebdab02c6efffb6e79a5d95128367", "generation_seconds_batch": 18.919371469994076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10621613264083862, "target_z": -0.5468749814091705, "ce": 6.197352409362793, "genuineness": 4.68307638168335, "identity": 0.5002983212471008, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b44324f527d4327161f1929621ba07c3109d871760d1739fba230ff5eaabafe9.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "b4b2fed04d0350c5be2534933e973804b20f2172bf03ad49b1ebe03004fe82c9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "38bec541df382c9e4cde96e76aaaae3adfc1f2a3ccb62c8876bb8760d3452592", "generation_seconds_batch": 16.77847273997031, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15689897537231445, "target_z": -0.4746093886111431, "ce": 6.197352409362793, "genuineness": 4.846253395080566, "identity": 0.600507915019989, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b4b2fed04d0350c5be2534933e973804b20f2172bf03ad49b1ebe03004fe82c9.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "b4cb312c858b2bebd9e2787189a0ea14680150efe991507aea239f1c1d2ddf40", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6bab8a77b2ba116ddb8bfe57dbc27ca1545473f4c1eb49530aed3f29125d7282", "generation_seconds_batch": 19.070308316964656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1979931890964508, "target_z": -0.41601564060301766, "ce": 5.974957466125488, "genuineness": 4.833701133728027, "identity": 0.6081786155700684, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b4cb312c858b2bebd9e2787189a0ea14680150efe991507aea239f1c1d2ddf40.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "b4fb273b45946c04e7f5ea693e4ea9b74bd70f59849b29bffa4661398e83e079", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4e18665313ea09f47222af012e3eb0e52c7034751d51da8be2b6b7dc12ace4a3", "generation_seconds_batch": 19.399268364999443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02402767539024353, "target_z": -0.664062519918746, "ce": 6.054384231567383, "genuineness": 4.532451152801514, "identity": 0.3593641519546509, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b4fb273b45946c04e7f5ea693e4ea9b74bd70f59849b29bffa4661398e83e079.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "b555950af33bda8e553d4b4b7010d00644b669430e0ef888e4d2762a53a1afc3", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3072a8faacb54c201814709cbeeb597f5d3dc8e5748c1ef4a7b807825297a266", "generation_seconds_batch": 14.301091230940074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7801612615585327, "target_z": 0.414062519918746, "ce": 5.863759994506836, "genuineness": 4.457139015197754, "identity": 0.511637270450592, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b555950af33bda8e553d4b4b7010d00644b669430e0ef888e4d2762a53a1afc3.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": "b5c555c4127e722fc90f3fd03c54565edfc4d7a0c22ae2c8872e427bc47b9892", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da8fed5260b708ce92cfb17ae5fc753e7d0fc4c2545e6f768b2130e6f9125054", "generation_seconds_batch": 14.401093303924426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.029466152191162, "target_z": 0.7695312493360418, "ce": 5.982900142669678, "genuineness": 4.532451152801514, "identity": 0.45232200622558594, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lun terug.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b5c555c4127e722fc90f3fd03c54565edfc4d7a0c22ae2c8872e427bc47b9892.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "b6843730215082a497818d0672c94b153ce07e98af30ecb4d76e6dfe9bd392e2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "140f72161b64cc2cee72588557943d4804063d2268a51036a619ae38df8260a9", "generation_seconds_batch": 19.09745725407265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24867606163024902, "target_z": -0.3437500053116656, "ce": 6.165581703186035, "genuineness": 4.432034492492676, "identity": 0.3757677674293518, "hypothesis": "The 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_Disappointment/b6843730215082a497818d0672c94b153ce07e98af30ecb4d76e6dfe9bd392e2.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": "b728406c78d81be26f8aefc57a0b9e4f29a8f721fe5c4b2ed0d4a498136d4d72", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "773e8dc5f7b47b394b416af4bf90d96032102b78c400de0bdfd5dc4c49bc92e8", "generation_seconds_batch": 15.049087673891336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8787873983383179, "target_z": 0.5546875491329067, "ce": 5.681078910827637, "genuineness": 4.306513786315918, "identity": 0.11720558255910873, "hypothesis": "De sleutels liggen op de keukentafel keken de la naast het raam neem ze mee als je weggaat.", "wer": 0.22727272727272727, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b728406c78d81be26f8aefc57a0b9e4f29a8f721fe5c4b2ed0d4a498136d4d72.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "b7537ef0a2d2ab47ab07a397af688ff95d911bb7c2d46230adbdf2f202421921", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b20305cc105d430f1fe23a1fe743f1e4f70beb5d25da3a94ed0f9003dc076752", "generation_seconds_batch": 19.29934238793794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4760640561580658, "target_z": -0.019531249336041803, "ce": 5.3792572021484375, "genuineness": 4.557555198669434, "identity": 0.7865502238273621, "hypothesis": "J'ai trouvé la 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_Disappointment/b7537ef0a2d2ab47ab07a397af688ff95d911bb7c2d46230adbdf2f202421921.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "b75b6f01a55e228f70f0e7e66b143d9b96a1b2d51bad2c8b0b13916730d56516", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0d90e22ef6f34e1871c6732597f079dd5a82d65a2d361bda768610a41c717f51", "generation_seconds_batch": 19.226010998012498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2336081862449646, "target_z": -0.3652343753319791, "ce": 5.935244083404541, "genuineness": 4.6705241203308105, "identity": 0.8150328993797302, "hypothesis": "La porte 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_Disappointment/b75b6f01a55e228f70f0e7e66b143d9b96a1b2d51bad2c8b0b13916730d56516.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": "b767001a46519012b23ecb2605a2f09e6ce0b6513f977717abb2ea12fddc81da", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "db8d1ee68a7a13948ffc891881430ea7486ff9271affec1f1706e081782d3d91", "generation_seconds_batch": 14.877004430047236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41442275047302246, "target_z": -0.10742185010156755, "ce": 5.677107334136963, "genuineness": 4.68307638168335, "identity": 0.44854414463043213, "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_Disappointment/b767001a46519012b23ecb2605a2f09e6ce0b6513f977717abb2ea12fddc81da.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "b82c71d47320bbe2e762a005ba300da67ffa2746ab7773c559d02916ea6169be", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "badfecb54cfe71d01ec3c6c746b2a37f2af7228e754b045683349c46030a29e4", "generation_seconds_batch": 19.947675686096773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16785743832588196, "target_z": -0.45898438064364466, "ce": 5.982900142669678, "genuineness": 4.281409740447998, "identity": 0.4177582561969757, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/b82c71d47320bbe2e762a005ba300da67ffa2746ab7773c559d02916ea6169be.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": "b8a5d5cd43cc05181235e1ee38faf8ef3b61a51533f1e0b7a2c197143f9bbd1b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0169411275be68fe1886df03d541b784deb534b50350f515086d8bc300e8b41", "generation_seconds_batch": 19.372340533998795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.333604097366333, "target_z": -0.22265626792687138, "ce": 5.446769714355469, "genuineness": 4.457139015197754, "identity": 0.7004619836807251, "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_Disappointment/b8a5d5cd43cc05181235e1ee38faf8ef3b61a51533f1e0b7a2c197143f9bbd1b.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "b9aba43a42349a470859061cf1efae6798a0bf597cbca4cf1bd6a63828d95a97", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fe0a07341c936e5de0215d8d43bc81dea6a3fb9eb6bfeb58115a306ac9b17e6e", "generation_seconds_batch": 21.89223956502974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.051423847675323486, "target_z": -0.6249999787533377, "ce": 6.157639026641846, "genuineness": 4.7458367347717285, "identity": 0.4489097595214844, "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_Disappointment/b9aba43a42349a470859061cf1efae6798a0bf597cbca4cf1bd6a63828d95a97.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "ba280854239eabd6019fe685ebcd8bab1ba8c858d4e6b555402d452aa2fc78a8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "dfa65ca8992fb75463758a5a7b9e11077d46024afe0bf1637ebd8f6c508ef964", "generation_seconds_batch": 19.284784403978847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16374802589416504, "target_z": -0.46484374269645984, "ce": 6.141753673553467, "genuineness": 4.143336772918701, "identity": 0.16600629687309265, "hypothesis": "The 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_Disappointment/ba280854239eabd6019fe685ebcd8bab1ba8c858d4e6b555402d452aa2fc78a8.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": "ba2d63649b5b828b878f436d4490de14287f05cb868848d72d47b8e15961b913", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8bdf7c749e39bfa81e1d712803fcd2fdb9117e88f25769d6c96b05a50f8014d6", "generation_seconds_batch": 15.169827741920017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44592830538749695, "target_z": -0.06249998937666882, "ce": 5.355429172515869, "genuineness": 4.507347106933594, "identity": 0.8132721185684204, "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_Disappointment/ba2d63649b5b828b878f436d4490de14287f05cb868848d72d47b8e15961b913.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "ba4165c411affd70425fc622f9cb55170f2680fa2fbc2e5781974060ce66e5b6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a4b43b078baddc72140a4c7cc6715beae07250bc9e190f7bd87128ccfb4adad9", "generation_seconds_batch": 20.37914442399051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006108075380325317, "target_z": -0.707031259959373, "ce": 6.38003396987915, "genuineness": 4.362998008728027, "identity": 0.5650026798248291, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ba4165c411affd70425fc622f9cb55170f2680fa2fbc2e5781974060ce66e5b6.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "adcb48dd080298c9810ebb92c0adac5a00a1af0feb5b05594cf594a13243a8a2", "generation_seconds_batch": 14.645251529058442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14868015050888062, "target_z": -0.48632811271677334, "ce": 6.197352409362793, "genuineness": 4.432034492492676, "identity": 0.6793321371078491, "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_Disappointment/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "bbb9392b07357df01e4f1137a07f910fed0120f64e82c95029a86852dc46ac5d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e85fcc91bf9a3fa0ed40b0afbf0f376315e852ebba01842953ff6ca8f11d7c57", "generation_seconds_batch": 19.332624329952523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5020903944969177, "target_z": 0.017578128651770095, "ce": 5.919358730316162, "genuineness": 4.833701133728027, "identity": 0.5299227237701416, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bbb9392b07357df01e4f1137a07f910fed0120f64e82c95029a86852dc46ac5d.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "bbbfc45df4fc58a0564184cad985c6cd5a2e90428d3a1480c1351fa8946eb75f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "82e7003abc497a348d257a82945812c8a954cdb9dbe7a0c640f7c32639f68730", "generation_seconds_batch": 19.173974264995195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19251397252082825, "target_z": -0.4238281233401045, "ce": 6.0305562019348145, "genuineness": 4.833701133728027, "identity": 0.7464385628700256, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bbbfc45df4fc58a0564184cad985c6cd5a2e90428d3a1480c1351fa8946eb75f.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "bc268546c3f093822ed0dd004d3352a74d3abfe2ee10a018ab0a48cff6ae87a4", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bdcaf3ede3731439ac389dbde0a78646381a62b85ae15e223eafe00e3802b269", "generation_seconds_batch": 15.99763045203872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12813302874565125, "target_z": -0.5156250079674984, "ce": 6.38797664642334, "genuineness": 4.7081804275512695, "identity": 0.42108190059661865, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bc268546c3f093822ed0dd004d3352a74d3abfe2ee10a018ab0a48cff6ae87a4.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "bc89e8a7afab27f0b02aae55c57e100954312532bc5eb57bc539a0e398eecf3c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c7fda5c8a5e8930205b7a3d560d313f2653ca2e2324cb1953127e72004ea8ec7", "generation_seconds_batch": 19.419519890099764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4089435040950775, "target_z": -0.1152343753319791, "ce": 5.700935363769531, "genuineness": 4.7081804275512695, "identity": 0.6982221007347107, "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_Disappointment/bc89e8a7afab27f0b02aae55c57e100954312532bc5eb57bc539a0e398eecf3c.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": "bc8d01b1d8b7b545c36db829af0a12f01bfc690d75a9e462572c00be640a6347", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f5189ad6ad8b3f1497a375e55f690aa214f189a65044442367f4c81a6bf32849", "generation_seconds_batch": 19.30290964397136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29250991344451904, "target_z": -0.2812499734416721, "ce": 5.871703147888184, "genuineness": 4.482243061065674, "identity": 0.7805110812187195, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue, elle était d'ici, près de la grande bibliothèque, nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bc8d01b1d8b7b545c36db829af0a12f01bfc690d75a9e462572c00be640a6347.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "bca53a08c8df6f9eab7b94fe7493a7b44337b0e5a9030e47f236613d02dfaf1b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "52ff64e1c2159981cd721993820f047bfbb96c148b9b6e4d437b03c0f1ac1d06", "generation_seconds_batch": 19.75363880605437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6192089319229126, "target_z": 0.18457035084358597, "ce": 5.871703147888184, "genuineness": 4.7834930419921875, "identity": 0.6650097966194153, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bca53a08c8df6f9eab7b94fe7493a7b44337b0e5a9030e47f236613d02dfaf1b.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "bce45b0617ac264545affbf286cb6a3f5bf8a7c6d4aeae08dd87b99c2144d556", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "eb2b9dcca766ead2f92ee41512569122cab4f3b375283b1190bfcee3948fdb3b", "generation_seconds_batch": 21.790112674003467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2445666491985321, "target_z": -0.3496093673644807, "ce": 5.542081832885742, "genuineness": 4.595211505889893, "identity": 0.5079626441001892, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bce45b0617ac264545affbf286cb6a3f5bf8a7c6d4aeae08dd87b99c2144d556.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "bceede5e14c76eac3141e715020609cf7abc239a241ea134baf1fcdafa2ae8ae", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "79b8740a60e592a4503717eff7d7895cf90ae28436867874a4a0884244eb5d4d", "generation_seconds_batch": 22.800505244988017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21443089842796326, "target_z": -0.39257810740510773, "ce": 6.2767791748046875, "genuineness": 4.632867813110352, "identity": 0.6436426639556885, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bceede5e14c76eac3141e715020609cf7abc239a241ea134baf1fcdafa2ae8ae.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": "bcf6c47d90c5e81525dc206cdf2b127bba7cd5c807b9f657d1bf5b3cec9659f5", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1b0642ab6ab558fed98158ee6f5f3c112e9e4aa95579db7d02362f4484def77", "generation_seconds_batch": 15.164338810020126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21032145619392395, "target_z": -0.3984375119512476, "ce": 5.538110733032227, "genuineness": 4.582659721374512, "identity": 0.58128821849823, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem Hohenbücherregal. 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_Disappointment/bcf6c47d90c5e81525dc206cdf2b127bba7cd5c807b9f657d1bf5b3cec9659f5.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "bd2a168164587f40f70a14be747ed3aa7d1a990a488e4462b45c2bb1fba1387c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75046a6669ea619b52ed67f25eec160530c0ae19728c59af8e56eba24052f9bc", "generation_seconds_batch": 15.595077709993348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5335959792137146, "target_z": 0.06250003186999355, "ce": 5.772419452667236, "genuineness": 4.7081804275512695, "identity": 0.7145248651504517, "hypothesis": "Et je venais, j'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bd2a168164587f40f70a14be747ed3aa7d1a990a488e4462b45c2bb1fba1387c.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "bd45d88af47724ac3cccfd6b430b1425a82b7a973ca85af26c25264e6b34db87", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "36034a06c21e3cb21d382dcf5daee4f90fbb76c5122b88b7d9517b5d94303aa0", "generation_seconds_batch": 19.267409572028555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3431927561759949, "target_z": -0.2089843806436447, "ce": 5.7684478759765625, "genuineness": 4.720732688903809, "identity": 0.4080238938331604, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bd45d88af47724ac3cccfd6b430b1425a82b7a973ca85af26c25264e6b34db87.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "bd66eab0b40f3948a673262a0d856637a28d64af2cf6a1202c698009da10e2bc", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3537305666ede86c0571364b91e7f33f003720dbfb4c3b734f309ef9513bc856", "generation_seconds_batch": 22.045023040962406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2116912603378296, "target_z": -0.3964843912669759, "ce": 6.23706579208374, "genuineness": 4.344170093536377, "identity": 0.30208486318588257, "hypothesis": "The 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_Disappointment/bd66eab0b40f3948a673262a0d856637a28d64af2cf6a1202c698009da10e2bc.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "bd73b437310c6141a0fc24d1caec4ddc7e458703f997965212a569bbf44d921a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7c7331541d281ee3b5d44e25c739ee00d1e048c7a760ce62f1d605b053c9384c", "generation_seconds_batch": 19.10833036492113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33497393131256104, "target_z": -0.22070310474927493, "ce": 5.617537498474121, "genuineness": 4.595211505889893, "identity": 0.6014910340309143, "hypothesis": "La porte 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_Disappointment/bd73b437310c6141a0fc24d1caec4ddc7e458703f997965212a569bbf44d921a.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "bdd3e3284b2bee41171351d24d932dea35eca743839d621bc825cb5f5431ec78", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9dc5b0cfa9330080f7dd47d5bd4e86e3a4658f4eb11fe4af64096f0cafe1c17f", "generation_seconds_batch": 14.37995256204158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16511783003807068, "target_z": -0.4628906220121881, "ce": 6.221180438995361, "genuineness": 4.582659721374512, "identity": 0.757922887802124, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bdd3e3284b2bee41171351d24d932dea35eca743839d621bc825cb5f5431ec78.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "bde1b977ea06eb10df59d0471d7d3396644fa30a9f4ade9b31c3a673e83015ca", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1f360d458751e647f6b0f97f3482b022f68a0e86412a49991a9d1eefe647e9cb", "generation_seconds_batch": 14.547612101072446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16100841760635376, "target_z": -0.46874998406500323, "ce": 6.109982967376709, "genuineness": 4.796044826507568, "identity": 0.7652105689048767, "hypothesis": "J'ai trouvé la 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_Disappointment/bde1b977ea06eb10df59d0471d7d3396644fa30a9f4ade9b31c3a673e83015ca.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": "be1b1fe550999dfc884d4fb216cd3f15433f07b6f4ff168ca78872c57c1a849e", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ae7b162e78db02cfcac0a2492af784c6094ef5fff4da397c4a9c6bfab44eaa9c", "generation_seconds_batch": 19.404544097953476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.226759135723114, "target_z": -0.3750000212466624, "ce": 5.454712867736816, "genuineness": 4.519899368286133, "identity": 0.5086467266082764, "hypothesis": "Jemand hat dem kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/be1b1fe550999dfc884d4fb216cd3f15433f07b6f4ff168ca78872c57c1a849e.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "be40e2f976042856028358ea7d1c31061c6a0147990f6fdede8db59f5b3ea83c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "18df0ccc89ce3b92a8d1e67146c167d864d204b2299c32eeb3ca67c9f1db410b", "generation_seconds_batch": 22.526097730966285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0349453687667847, "target_z": 0.7773437320731287, "ce": 5.784333229064941, "genuineness": 4.607763767242432, "identity": 0.7119804620742798, "hypothesis": "J'ai trouvé la 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_Disappointment/be40e2f976042856028358ea7d1c31061c6a0147990f6fdede8db59f5b3ea83c.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "be443fbdbf7b497c20dfee83032a373338f069f9c976b2f7df04751cea69a9bd", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e49ce0f9937056c7dad9ae0a4d8c36a13afd61c01d65153f4c8e344af7e68395", "generation_seconds_batch": 14.265144537086599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9554965496063232, "target_z": 0.6640624774254212, "ce": 6.0146708488464355, "genuineness": 4.896461486816406, "identity": 0.7901523113250732, "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_Disappointment/be443fbdbf7b497c20dfee83032a373338f069f9c976b2f7df04751cea69a9bd.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "bf03597cc3f5da006a42a91fa5b68bfbb4dd9128e3dfe5ab38425949d849356a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ace6a3e2f2cc3fc6be20a7ef14d3d3d1b1affba9f7d0284cb1f020fa7a00b27e", "generation_seconds_batch": 19.088805068051443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21717050671577454, "target_z": -0.38867186603656434, "ce": 5.681078910827637, "genuineness": 4.632867813110352, "identity": 0.576410174369812, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bf03597cc3f5da006a42a91fa5b68bfbb4dd9128e3dfe5ab38425949d849356a.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "bf062d5035536d8069ad6b547e0222fc1619632a508b720f0edb472092410481", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37aa2da1067db5456c39147b8b41089e311aa98541c12cd8b00dad5c8945af05", "generation_seconds_batch": 14.38312038499862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31442680954933167, "target_z": -0.25, "ce": 5.657250881195068, "genuineness": 4.7834930419921875, "identity": 0.7892881631851196, "hypothesis": "La portée 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_Disappointment/bf062d5035536d8069ad6b547e0222fc1619632a508b720f0edb472092410481.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "bfc60c07c913288559bc6299492e8196ec818823d0b8282451a74a2bab6168fe", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3a06f27ff2726e76d4c95cb8a1fadeed4467285e405826dbcbe1e9694a3aa27f", "generation_seconds_batch": 16.3869332219474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16648763418197632, "target_z": -0.4609375013279164, "ce": 5.927301406860352, "genuineness": 4.959221839904785, "identity": 0.6881893873214722, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/bfc60c07c913288559bc6299492e8196ec818823d0b8282451a74a2bab6168fe.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "bff6c81ee5f9e2a7af1adb8f2ab08285effe96e0e2b28827792ab5f37bdd3357", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "dd47cfae7f393ceaf29ef1e15d40a5fd866c68c8a3e07de6ca419cdb6fc88d77", "generation_seconds_batch": 16.020156911108643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20073282718658447, "target_z": -0.4121093567411495, "ce": 6.229123115539551, "genuineness": 4.356721878051758, "identity": 0.5209286212921143, "hypothesis": "The 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_Disappointment/bff6c81ee5f9e2a7af1adb8f2ab08285effe96e0e2b28827792ab5f37bdd3357.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "c03318ce7cbd0534aac8ef1f1672d10d34c3e8994ba5dd4e64fcd8434364df5c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "29d65aa1ede5872af623be6f3fbce2c157a15a6b87acec3cd1be60b93ed189b9", "generation_seconds_batch": 22.336280976072885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23223838210105896, "target_z": -0.3671874960162508, "ce": 6.086154937744141, "genuineness": 4.7332844734191895, "identity": 0.7146034836769104, "hypothesis": "La porte 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_Disappointment/c03318ce7cbd0534aac8ef1f1672d10d34c3e8994ba5dd4e64fcd8434364df5c.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "c07db9c18bd93c3689dec49a3ba8718c9c157efa402b45ffed6f96a2b9054402", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e68efa1c51ea2704fd2fb1ab65937f5c1a585075e9f2ffebc4c8af0067db0178", "generation_seconds_batch": 15.660503581049852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4253811836242676, "target_z": -0.09179688462739388, "ce": 5.613565921783447, "genuineness": 4.68307638168335, "identity": 0.7686454057693481, "hypothesis": "La porte 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_Disappointment/c07db9c18bd93c3689dec49a3ba8718c9c157efa402b45ffed6f96a2b9054402.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "c0993e940d7c642e58de4eafa9296cdb1687839a620ef465430811f370d03b50", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "422272781342bf90fb93ef60ad597587d34064cce206e9e985e3348813ed296e", "generation_seconds_batch": 19.28015595697798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12265381217002869, "target_z": -0.5234374907045852, "ce": 5.9431867599487305, "genuineness": 4.607763767242432, "identity": 0.5616949796676636, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c0993e940d7c642e58de4eafa9296cdb1687839a620ef465430811f370d03b50.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "c140f7187fed90aa857264d5b413436260080b3e4e045608cb9728a926a2713c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0096327f399c4c9b9cb2a9685abf90f0a3eaf54c1d1c7894533880a57e0bd1f9", "generation_seconds_batch": 19.854002356063575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08429920673370361, "target_z": -0.5781249973441672, "ce": 6.300607204437256, "genuineness": 4.7081804275512695, "identity": 0.325278639793396, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c140f7187fed90aa857264d5b413436260080b3e4e045608cb9728a926a2713c.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "c19c1241421ad223387395e9615990eb202daaec35ce6095e4e70db0a5fb073c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2fe2c7b1bf74f101bc11579bed3f2d89dae31ef927576fb21e4af185a0af058f", "generation_seconds_batch": 14.550586065044627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23771759867668152, "target_z": -0.359375013279164, "ce": 6.109982967376709, "genuineness": 4.607763767242432, "identity": 0.599244236946106, "hypothesis": "La porte 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_Disappointment/c19c1241421ad223387395e9615990eb202daaec35ce6095e4e70db0a5fb073c.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "c2d74244a6197d32277f11ae394c809c199f98cde6c5e7c5877495b4565c7049", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ca8a441cd7f1ef6c45a6b9f19ec7b38bb561ef15e475f247d0672e3d20a9e669", "generation_seconds_batch": 19.95152410492301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1555291712284088, "target_z": -0.47656250929541477, "ce": 6.086154937744141, "genuineness": 4.833701133728027, "identity": 0.6410826444625854, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c2d74244a6197d32277f11ae394c809c199f98cde6c5e7c5877495b4565c7049.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "c2e4532b89141e25418e17699259ab92fbf87433329cf6a2d87f0f88422aca84", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "32e3a187b49a7c6330a7909c7dfc105e8bbb4bd624ef3f65f668ad184d5a81a0", "generation_seconds_batch": 19.3636993879918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1801857054233551, "target_z": -0.4414062519918746, "ce": 6.1894097328186035, "genuineness": 4.758388519287109, "identity": 0.6005663871765137, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c2e4532b89141e25418e17699259ab92fbf87433329cf6a2d87f0f88422aca84.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "6572b75c69532ee71f40b943399f26c1e604448d77d0c804fec6ef6e5e163875", "generation_seconds_batch": 16.38664360693656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18977436423301697, "target_z": -0.4277343647086479, "ce": 6.1894097328186035, "genuineness": 4.369274139404297, "identity": 0.7464512586593628, "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_Disappointment/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "c3b7b4a8a8ab9daf0f1913a6d28145ef60fefe0cdc3aaf187f578defe294de65", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e0aed471ae68eaeb2674f2f0070cb2943d9ad29964496206ecb110fe4966264f", "generation_seconds_batch": 19.275075062992983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28155142068862915, "target_z": -0.29687502390249515, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.7788931131362915, "hypothesis": "Ik 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_Disappointment/c3b7b4a8a8ab9daf0f1913a6d28145ef60fefe0cdc3aaf187f578defe294de65.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": "c3e665c0dc5b1c04d41a6684da551318bd7a478e671ab588c714e90054d974bf", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5eb12e44520753c48480901441621352a30611897e4922e3dd6b2ffcd9a4773a", "generation_seconds_batch": 14.378011813038029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4733244478702545, "target_z": -0.02343749070458522, "ce": 5.700935363769531, "genuineness": 4.545003414154053, "identity": 0.13815191388130188, "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_Disappointment/c3e665c0dc5b1c04d41a6684da551318bd7a478e671ab588c714e90054d974bf.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "c3eda5e7f46a466e8cd222bba9d7aee997c8fa12b184e36e2b3ba05e6fffa90f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fc64d9782a1d49aee48f71991547d1fd9ea3c1f361c2819f40846956ffeacff3", "generation_seconds_batch": 19.51532984606456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7418066263198853, "target_z": 0.35937497078583924, "ce": 5.681078910827637, "genuineness": 4.7458367347717285, "identity": 0.8128197193145752, "hypothesis": "J'ai trouvé la 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_Disappointment/c3eda5e7f46a466e8cd222bba9d7aee997c8fa12b184e36e2b3ba05e6fffa90f.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": "c4220cfe7c09d129587315e266b0e3a0277553037b83dce4741d3a8233f84949", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3642531a7d35b78b020b4917154081f04e32c8e296e83216a8d4b0c50305300", "generation_seconds_batch": 19.408722269930877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8157762289047241, "target_z": 0.46484374269645984, "ce": 5.974957466125488, "genuineness": 4.607763767242432, "identity": 0.7911240458488464, "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_Disappointment/c4220cfe7c09d129587315e266b0e3a0277553037b83dce4741d3a8233f84949.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "c45ddfc08cd49f2d24d6265f84ae6fb576c7841e2660771e6e35a19f42e11983", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "673d2ce01d14a258ae95519b94d43f9baf296679f85f484292d42b19bbd84e6e", "generation_seconds_batch": 19.160312504973263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37058889865875244, "target_z": -0.16992188197156108, "ce": 5.6413655281066895, "genuineness": 4.68307638168335, "identity": 0.7108657360076904, "hypothesis": "J'ai trouvé la 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_Disappointment/c45ddfc08cd49f2d24d6265f84ae6fb576c7841e2660771e6e35a19f42e11983.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "ab66aa21b27474da526bb82dc9de821d97bc2e3409d7e002f07446e43d8d4b06", "generation_seconds_batch": 17.060368397040293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13909149169921875, "target_z": -0.5, "ce": 6.260893821716309, "genuineness": 4.381826400756836, "identity": 0.7271094918251038, "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_Disappointment/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.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": "c4f17b50868b6164773f313b01080b9aa33b91747454d1744614e74e4d96479b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aced7888c4f014a6493366ce74ee533c72ffb906a71f4ffdd608eb3db499de5a", "generation_seconds_batch": 14.472820817958564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2842910587787628, "target_z": -0.292968740040627, "ce": 5.542081832885742, "genuineness": 4.293961524963379, "identity": 0.21458494663238525, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder tot aan het kleine houten hek. Ik wacht, aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c4f17b50868b6164773f313b01080b9aa33b91747454d1744614e74e4d96479b.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": "c6993d154f8130bc0f046bbd55667ef7f2ff80c6bd9771f6fe9e5f618946d131", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "246dccc7c099939eeca5b8b227cfb7e6a6a8bfee495e2c45a003b536d84fb5cc", "generation_seconds_batch": 19.610477454029024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21032145619392395, "target_z": -0.3984375119512476, "ce": 5.80021858215332, "genuineness": 4.607763767242432, "identity": 0.4750312864780426, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holstor. Ich warte auf der anderen Seite.", "wer": 0.047619047619047616, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c6993d154f8130bc0f046bbd55667ef7f2ff80c6bd9771f6fe9e5f618946d131.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "c6a08355a27a5b0b26775fc724911c572416e420651fb0c07e6abda77a4b0aad", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a03cada3f577bef13998e6a1d08693a0afd137445df353aa40a9c0e802f9dc6d", "generation_seconds_batch": 14.392381074023433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47058483958244324, "target_z": -0.02734373207312863, "ce": 6.078212261199951, "genuineness": 4.557555198669434, "identity": 0.3351828455924988, "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_Disappointment/c6a08355a27a5b0b26775fc724911c572416e420651fb0c07e6abda77a4b0aad.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "c6f47fa7a18bf323d37581172d58bedc7707bf43f541ee8772ae20777ec43cc2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f6346df6dcf38e8714654ab5e100c17540e829e5654ca71a73d4737bc0d5db21", "generation_seconds_batch": 14.39339292095974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.366438627243042, "target_z": 1.2499998725200259, "ce": 6.141753673553467, "genuineness": 4.6203155517578125, "identity": 0.46702033281326294, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c6f47fa7a18bf323d37581172d58bedc7707bf43f541ee8772ae20777ec43cc2.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "c6f4cbef0fdccb219dad8b9c44e57bc4ffddc994fcaab8de295e28ccbd2b672c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2f1b11be9889b3f53e278a2c4b3cf1f185287f64005069305a9c7883f4c1f045", "generation_seconds_batch": 19.049944333033636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18566492199897766, "target_z": -0.43359376925478776, "ce": 5.871703147888184, "genuineness": 4.68307638168335, "identity": 0.4061165452003479, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c6f4cbef0fdccb219dad8b9c44e57bc4ffddc994fcaab8de295e28ccbd2b672c.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "c78b9edf7ffe9a19aaa0c93155cb006d87a85a2bb8bea1e0cd0512bae28c7ac1", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3e6f79b0e5a977668776fb7dac2f0b57a2e1c6e1d9484e34194504bb10ef3860", "generation_seconds_batch": 18.18502020498272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08977842330932617, "target_z": -0.5703125146070803, "ce": 6.252951145172119, "genuineness": 4.256305694580078, "identity": 0.5555428266525269, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c78b9edf7ffe9a19aaa0c93155cb006d87a85a2bb8bea1e0cd0512bae28c7ac1.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "c7d78dac6ef7a2e8241c450be32f9f691878ae0d3cda2c3fa733abb8e8aca520", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "695a019a59a085ab50967f1a5654cd76be5eec78e00184a2c13b19f24909cc53", "generation_seconds_batch": 19.167338444967754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2897702753543854, "target_z": -0.28515625730354016, "ce": 6.022613525390625, "genuineness": 4.7332844734191895, "identity": 0.7592771053314209, "hypothesis": "Die Tür 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_Disappointment/c7d78dac6ef7a2e8241c450be32f9f691878ae0d3cda2c3fa733abb8e8aca520.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "c7eaaca5cdd9fed75b71d970cbfe2ac8d478f23473a2e1fe7e0ad9dca0951fe3", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0096dd16a83449df90a6fe9032755e1004e5b83a781869a3b2754b13b72d35dc", "generation_seconds_batch": 22.451061881962232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19251397252082825, "target_z": -0.4238281233401045, "ce": 6.022613525390625, "genuineness": 4.519899368286133, "identity": 0.4210917353630066, "hypothesis": "The 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_Disappointment/c7eaaca5cdd9fed75b71d970cbfe2ac8d478f23473a2e1fe7e0ad9dca0951fe3.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "f1cd116027cf2283177d731228f266767d65ed6351581e969b3eddc9a6f3df04", "generation_seconds_batch": 18.707228335086256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21717050671577454, "target_z": -0.38867186603656434, "ce": 6.205295085906982, "genuineness": 4.319066047668457, "identity": 0.6669657230377197, "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_Disappointment/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "c85f1dfd1436d33658d44fb09b021cb1c6b67fcd10afacbf945cde650e576020", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "697ba2121fc64475819dcb44850881508bb7f35de5409869de1675a88f3c3edd", "generation_seconds_batch": 19.993047722964548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20073282718658447, "target_z": -0.4121093567411495, "ce": 6.197352409362793, "genuineness": 4.507347106933594, "identity": 0.5701370239257812, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c85f1dfd1436d33658d44fb09b021cb1c6b67fcd10afacbf945cde650e576020.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": "c87148e3783c6ad0245411c5f9e88c246c0112f5e2610435729145f12738c93d", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a8e0fe52a66043a6497232fb908c4038fc10aebbe9adc296af0fefd45ea524a", "generation_seconds_batch": 14.765076454961672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42401137948036194, "target_z": -0.0937500053116656, "ce": 5.418970584869385, "genuineness": 4.570107460021973, "identity": 0.5217249393463135, "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_Disappointment/c87148e3783c6ad0245411c5f9e88c246c0112f5e2610435729145f12738c93d.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "516566e5129e7c16cee624fb9c649e3913515f7d5e03b55308c6f9948591e3a0", "generation_seconds_batch": 14.553182182018645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20073282718658447, "target_z": -0.4121093567411495, "ce": 6.316492557525635, "genuineness": 4.337893962860107, "identity": 0.3815988600254059, "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_Disappointment/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "c8c0c99f2f267d418382b1fd615953c5dc19cfa2fe48b64bba7124d4426a3c9d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "86298c919f01a6746edd4a0ec9295f075fb1fb2156d3240b84d58fda1d1558a5", "generation_seconds_batch": 14.19633239810355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41031330823898315, "target_z": -0.11328125464770739, "ce": 5.577824115753174, "genuineness": 4.7081804275512695, "identity": 0.7115651369094849, "hypothesis": "J'ai trouvé la 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_Disappointment/c8c0c99f2f267d418382b1fd615953c5dc19cfa2fe48b64bba7124d4426a3c9d.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "c8de9a8e2d5ecc1368ffe0dc6c25e1fc7a4687f16743df34aa08acee0c6d012b", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fa2847d39e8d4516ec90f3ff82278a78268abe35658679b9f71603465849984d", "generation_seconds_batch": 15.694644161965698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1582687795162201, "target_z": -0.4726562679268714, "ce": 6.197352409362793, "genuineness": 4.7081804275512695, "identity": 0.6831903457641602, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c8de9a8e2d5ecc1368ffe0dc6c25e1fc7a4687f16743df34aa08acee0c6d012b.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "c8e779e50639f1bc0ebaa15bac934317bb45822ff4c3f323f7e07caee01a049e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "82a0eed8221aac3315524e8dc3c51b1fce005f32873a8ce8abe849fc47d893c7", "generation_seconds_batch": 19.280703464057297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7664631605148315, "target_z": 0.39453122808937946, "ce": 6.086154937744141, "genuineness": 4.419482707977295, "identity": 0.6403990387916565, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c8e779e50639f1bc0ebaa15bac934317bb45822ff4c3f323f7e07caee01a049e.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "c910ebe3d479a0ce4a5a6afa438f37476466d1c01607bb7accae91c269040cba", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "83e8955fac3bfd2cc4601001a8704e6f1cca03cedbd4a42d1514ae32a000b750", "generation_seconds_batch": 14.39339292095974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25963452458381653, "target_z": -0.3281249973441672, "ce": 6.078212261199951, "genuineness": 4.494794845581055, "identity": 0.620197057723999, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c910ebe3d479a0ce4a5a6afa438f37476466d1c01607bb7accae91c269040cba.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "c949cc04ca4f230116aa0b23b7f532dad4c4238ff3d31d8903648f86fb8f3281", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "129e13c48efd95c2c13272218e494bf6cb2240ce829beb3256c558ccb6f92a0d", "generation_seconds_batch": 22.265932583017275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.328084111213684, "target_z": 1.195312493360418, "ce": 5.95112943649292, "genuineness": 4.557555198669434, "identity": 0.45418593287467957, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c949cc04ca4f230116aa0b23b7f532dad4c4238ff3d31d8903648f86fb8f3281.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "c96b53d90c1612d8f2df45ec6dd94d62b0d890b8326e0d85246cc9930750837c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6512777996cd254897e63dba5075292114f0b3ddb45e7e7d2ab544fee4dc010e", "generation_seconds_batch": 19.275460788980126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8623496890068054, "target_z": 0.5312500159349968, "ce": 5.736677646636963, "genuineness": 4.469690799713135, "identity": 0.5081728100776672, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c96b53d90c1612d8f2df45ec6dd94d62b0d890b8326e0d85246cc9930750837c.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "c998ebdc6e9769d4e4ad0badd770e18c9ddd4ce1dc5d5ce25d1f330bb52796b7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c6078e3e426ff74d899c8f00805ab2295c84e1a07c5ff384514874674e7404d6", "generation_seconds_batch": 16.113613507011905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8308441042900085, "target_z": 0.48632811271677334, "ce": 6.038498878479004, "genuineness": 4.432034492492676, "identity": 0.6386129260063171, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c998ebdc6e9769d4e4ad0badd770e18c9ddd4ce1dc5d5ce25d1f330bb52796b7.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "c9a73d291f5dc0dc2d74fa1ecdfdbe58e6350fefe80153e7531eb6f3ee0b8f66", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2e8b53a3eef251c06fa431e048bb5e9620cc14bff0038aa29bdfd0aab77aca66", "generation_seconds_batch": 19.134846278000623, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.482913076877594, "target_z": -0.009765645914683263, "ce": 6.062326908111572, "genuineness": 4.632867813110352, "identity": 0.4487302303314209, "hypothesis": "Ik 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_Disappointment/c9a73d291f5dc0dc2d74fa1ecdfdbe58e6350fefe80153e7531eb6f3ee0b8f66.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "c9bc92e125e3e327cb31d05b1ac3c61ab8bb6e9f67d8b20b8d5003a928ddb5dd", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "017e9cfcfb4c68ae5514dce7ec923e250549dcb968299a7f7fd0aeddcf6707f0", "generation_seconds_batch": 19.270680351066403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18292531371116638, "target_z": -0.43750001062333116, "ce": 6.09409761428833, "genuineness": 4.8588056564331055, "identity": 0.5262795686721802, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c9bc92e125e3e327cb31d05b1ac3c61ab8bb6e9f67d8b20b8d5003a928ddb5dd.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "c9cdee847cb754eaa3e87a90fef3d045aad3bd564238d19f77a4641c3cad98ab", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0fd08a340e397c67c3036009e135ebb256eab7b5d82ebb7a451d12a2dd7a979b", "generation_seconds_batch": 22.248959227930754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24730625748634338, "target_z": -0.3457031259959373, "ce": 5.8875885009765625, "genuineness": 4.331617832183838, "identity": 0.720283031463623, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/c9cdee847cb754eaa3e87a90fef3d045aad3bd564238d19f77a4641c3cad98ab.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": "ca1287eee3d62f1dfcbe948632ecf4723ae8dea146070cbdc6046f8a656763fe", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a0093dd2f3917c57777f4a2b0dc40695e78bdc0872db39430d004606ad3578c", "generation_seconds_batch": 14.877004430047236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49524134397506714, "target_z": 0.007812482737086831, "ce": 5.5817952156066895, "genuineness": 4.821148872375488, "identity": 0.4603601098060608, "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_Disappointment/ca1287eee3d62f1dfcbe948632ecf4723ae8dea146070cbdc6046f8a656763fe.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "cc23c3d324652514a238769cc2e0f79b405c85434d09646d6d676eb6d1b8d67e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a31f4fcf9b10029eb605c465e94cf4e4ce5a81d999aafc5d3f201f0482877eb", "generation_seconds_batch": 19.658303936943412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17744609713554382, "target_z": -0.445312493360418, "ce": 6.046441555023193, "genuineness": 4.394378662109375, "identity": 0.6981012225151062, "hypothesis": "La porte 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_Disappointment/cc23c3d324652514a238769cc2e0f79b405c85434d09646d6d676eb6d1b8d67e.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "cc3f05182105a0a1797626ffab6421ba4e9204d645b98b47a5eaa0be4d56c330", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0e61c322341e14d093153574aacc9ae93927de4efdf310fbcdd15e8898fc311b", "generation_seconds_batch": 19.380403013899922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1801857054233551, "target_z": -0.4414062519918746, "ce": 5.935244083404541, "genuineness": 4.808597087860107, "identity": 0.7471442818641663, "hypothesis": "J'ai trouvé la 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_Disappointment/cc3f05182105a0a1797626ffab6421ba4e9204d645b98b47a5eaa0be4d56c330.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "cc69f3fb6a7f385140136e884f921ad7910d011bd9a51bc314c5ea88379128f7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c38765fecbc520e6149475782db8884e28d8eb95b662ae8f100254c85d2147d2", "generation_seconds_batch": 19.075813103001565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7281085848808289, "target_z": 0.33984376394312216, "ce": 5.919358730316162, "genuineness": 4.3881025314331055, "identity": 0.316586971282959, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/cc69f3fb6a7f385140136e884f921ad7910d011bd9a51bc314c5ea88379128f7.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "ccace2e6ca892d4c216f9fb7ebd3023ccce2a67fbb9f88a822cdfd75a1b5bbd5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca26de906e47e8eb63d088ad4ebff029880d301319ba1dd815e2947cee2de600", "generation_seconds_batch": 19.426929025910795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2582647204399109, "target_z": -0.3300781180284389, "ce": 6.038498878479004, "genuineness": 4.331617832183838, "identity": 0.7502856254577637, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ccace2e6ca892d4c216f9fb7ebd3023ccce2a67fbb9f88a822cdfd75a1b5bbd5.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "ccc6866a0526c95ab0843cad265c46c18b063be2f62868ee2bda9db2a56dc788", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9684ddc6dc46aca99ea02c250b427b28a9ad824b97ff846716e85b4d0eb2d00e", "generation_seconds_batch": 14.242542922031134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19251397252082825, "target_z": -0.4238281233401045, "ce": 5.855817794799805, "genuineness": 4.595211505889893, "identity": 0.651067316532135, "hypothesis": "La porte 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_Disappointment/ccc6866a0526c95ab0843cad265c46c18b063be2f62868ee2bda9db2a56dc788.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "cd53edc42f311575a30c97b4368e2d72f7fd22b087ba06c808aaca8655447eae", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c6cc3635e0d3a83adbb6077391910e25a1a6f33980a6b466ab2b029f912fa269", "generation_seconds_batch": 23.013349346001633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24593645334243774, "target_z": -0.347656246680209, "ce": 5.1926045417785645, "genuineness": 4.582659721374512, "identity": 0.7384629249572754, "hypothesis": "La porte 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_Disappointment/cd53edc42f311575a30c97b4368e2d72f7fd22b087ba06c808aaca8655447eae.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "cd985bf7cb0da7a07534f3ac2cd2ae6ab81f97959660b75265b24f4e692e411d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "937ddd81c9967bc08a72e93a5ab3719006943e71f6bcb8dc4bcd6f8f17d844f0", "generation_seconds_batch": 19.227872506016865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26785337924957275, "target_z": -0.31640623074521224, "ce": 5.673136234283447, "genuineness": 4.720732688903809, "identity": 0.7469710111618042, "hypothesis": "La porte 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_Disappointment/cd985bf7cb0da7a07534f3ac2cd2ae6ab81f97959660b75265b24f4e692e411d.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "cdce8f38745d125dcbaea5945ccefd4a7aaf4e764bf65571c7ac8cff7e808504", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5b34ee96c03f5b15151360d2a92f033e712928f634d54ebc7ea918b11b5be240", "generation_seconds_batch": 19.369267383939587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2048422396183014, "target_z": -0.4062499946883344, "ce": 5.720792293548584, "genuineness": 4.883909225463867, "identity": 0.6133414506912231, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/cdce8f38745d125dcbaea5945ccefd4a7aaf4e764bf65571c7ac8cff7e808504.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "ce1d74d15eee7990567cee25629aae33b13b69d9a3b6fa0212065ffae86de14e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7674ce36cbe7b863d0795dbdfc3b3d823627f3b90936aeb85a81ce4fb96458fb", "generation_seconds_batch": 19.448294593021274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22812896966934204, "target_z": -0.37304685806906596, "ce": 5.990842819213867, "genuineness": 4.369274139404297, "identity": 0.48521068692207336, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ce1d74d15eee7990567cee25629aae33b13b69d9a3b6fa0212065ffae86de14e.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "ceaed50f577effe47205584330c60fecc8fd03c6a940ca9c1f1e7d3e63ba8f8b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ded984b6711365bc14ebfa8795bb357c0820dc354f0d59771ff58b8c369740da", "generation_seconds_batch": 14.333551007090136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40346425771713257, "target_z": -0.12304690056239065, "ce": 5.736677646636963, "genuineness": 4.821148872375488, "identity": 0.7976095676422119, "hypothesis": "J'ai trouvé la 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_Disappointment/ceaed50f577effe47205584330c60fecc8fd03c6a940ca9c1f1e7d3e63ba8f8b.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "cf594220e4d1f1b95a5444072db7253a9e83d748b9cf73d89382e9df92159264", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1a129e490cb128d71cabae92b7f7af749f77ec2b83453d01d0b5850137659750", "generation_seconds_batch": 19.776369470986538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08977842330932617, "target_z": -0.5703125146070803, "ce": 6.221180438995361, "genuineness": 4.218649387359619, "identity": 0.2672702968120575, "hypothesis": "The 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_Disappointment/cf594220e4d1f1b95a5444072db7253a9e83d748b9cf73d89382e9df92159264.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "cf5c00e664dd5bbcc27cb80001c940fae2537a60d02ca65ea63db9174600c8a6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0e1ef8659b0e330a987571829237ecdc72702aa3f86802ed31c85d06eae0b1d6", "generation_seconds_batch": 19.28105674800463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6527692079544067, "target_z": 0.23242191384155464, "ce": 5.919358730316162, "genuineness": 4.6705241203308105, "identity": 0.7785766124725342, "hypothesis": "J'ai trouvé la 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_Disappointment/cf5c00e664dd5bbcc27cb80001c940fae2537a60d02ca65ea63db9174600c8a6.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "951b32560611af29a21ff511f9b5f329baacc636678cfc13658329f215159c1b", "generation_seconds_batch": 14.951194775057957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07060113549232483, "target_z": -0.597656246680209, "ce": 6.3641486167907715, "genuineness": 4.168440818786621, "identity": 0.5298402309417725, "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_Disappointment/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "cfad81dc00d925ebfc547fdb2d26c150c2510de4593b3838d6e3526481fd6f9d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5f9b95cab91c73bd5dae17e0771220ddda2e72582aa387ae78de89edde6519c6", "generation_seconds_batch": 14.467672514962032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20758184790611267, "target_z": -0.402343753319791, "ce": 5.557967185974121, "genuineness": 4.7834930419921875, "identity": 0.4145686626434326, "hypothesis": "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_Disappointment/cfad81dc00d925ebfc547fdb2d26c150c2510de4593b3838d6e3526481fd6f9d.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "4a6220af2341524786c015578abed0e70f45d3de793b5331a7280b5bd2317f0f", "generation_seconds_batch": 16.053690223954618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11443495750427246, "target_z": -0.5351562573035402, "ce": 6.395919322967529, "genuineness": 4.024092197418213, "identity": 0.3266722559928894, "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_Disappointment/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "d1323c38fe7bf918a70c43460a8c6c26f9ade1326d8d06e7d9dc3deadd4a42f7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf5f432f793d155ea30e5bbf4056e5c26b31752e10f0cf4aecd6808f6aa7eddb", "generation_seconds_batch": 19.339680974022485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2226497232913971, "target_z": -0.3808593832994775, "ce": 5.7684478759765625, "genuineness": 4.7332844734191895, "identity": 0.7505491971969604, "hypothesis": "La porte 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_Disappointment/d1323c38fe7bf918a70c43460a8c6c26f9ade1326d8d06e7d9dc3deadd4a42f7.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "d161e0bf4ae4117354351eb2910dc40d1472f052e6c1b5d60397f126cbd2eceb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7e1791ac425f2fb537cc0c5503bba31f60bbce12762491161f9fbe3084a11e9f", "generation_seconds_batch": 19.158086092909798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07881999015808105, "target_z": -0.585937480081254, "ce": 5.982900142669678, "genuineness": 4.68307638168335, "identity": 0.6537666320800781, "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_Disappointment/d161e0bf4ae4117354351eb2910dc40d1472f052e6c1b5d60397f126cbd2eceb.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "d1731b5e50a50d28823b7eefb2b316e581e160df7d3d4bf2b8141ad83e649b9b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "40d16339f1a813829e4d39877e65ed52e8db18e0c4ad860d1a9f251bcebd9b93", "generation_seconds_batch": 19.13464008201845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2158007025718689, "target_z": -0.390624986720836, "ce": 5.307773113250732, "genuineness": 4.7081804275512695, "identity": 0.7958807945251465, "hypothesis": "J'ai trouvé la 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_Disappointment/d1731b5e50a50d28823b7eefb2b316e581e160df7d3d4bf2b8141ad83e649b9b.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "4885220bc83f9a112c20e7a02c0027556b44696edbd80abf696182ccd509aa48", "generation_seconds_batch": 16.50172446295619, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18840456008911133, "target_z": -0.4296874853929196, "ce": 6.117925643920898, "genuineness": 4.344170093536377, "identity": 0.7214924693107605, "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_Disappointment/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "d354c4c1efb631bff091edfab48cef14eb89fbb4c50062602e3c435036024e8a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9421a79456fd62feb574d8fe048f642def6509e0ce574403047644438296265f", "generation_seconds_batch": 19.304013716988266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2158007025718689, "target_z": -0.390624986720836, "ce": 6.292664527893066, "genuineness": 4.369274139404297, "identity": 0.21460819244384766, "hypothesis": "The 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_Disappointment/d354c4c1efb631bff091edfab48cef14eb89fbb4c50062602e3c435036024e8a.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": "d3565c2b4a7b7d2646fab10eb851ba9eec934f6d6731c27e4a40fb56af460945", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47135ecef867b101e1e8c85f729011ab888d0a7077d7159447ed0cc574cbd1ab", "generation_seconds_batch": 14.635168944019824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2651137709617615, "target_z": -0.32031247211375563, "ce": 5.542081832885742, "genuineness": 4.595211505889893, "identity": 0.6562881469726562, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stehen ihn nach dem Essen zurück.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d3565c2b4a7b7d2646fab10eb851ba9eec934f6d6731c27e4a40fb56af460945.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "d3cecfa29bbda842dfb7380a7ddf2e9dc175395193621268058de894d7a26c64", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ba82448721757ac8cd234533c9fad09ceb03670015c53946244f0f8fee78a714", "generation_seconds_batch": 19.03566255606711, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4185321629047394, "target_z": -0.10156248804875243, "ce": 5.156862258911133, "genuineness": 4.507347106933594, "identity": 0.663007915019989, "hypothesis": "J'ai trouvé la 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_Disappointment/d3cecfa29bbda842dfb7380a7ddf2e9dc175395193621268058de894d7a26c64.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "d3e76945dc71b9bfc38ea73442369cdfa09b9d52e162fae51cb406c668714f53", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1c07b32d7548dc21bcdda884a8eed844aafc7a7bcf567862f061b27dd9c9b90b", "generation_seconds_batch": 20.116676776087843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26100432872772217, "target_z": -0.3261718766598955, "ce": 6.181467056274414, "genuineness": 4.6956281661987305, "identity": 0.6945799589157104, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d3e76945dc71b9bfc38ea73442369cdfa09b9d52e162fae51cb406c668714f53.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "dcad5f3f3c976612a596205a76f8cdbb7aba05f788107f4b4c7742519e4115c5", "generation_seconds_batch": 16.603685406967998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.056903064250946045, "target_z": -0.6171874960162508, "ce": 5.831989288330078, "genuineness": 4.457139015197754, "identity": 0.5835233926773071, "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_Disappointment/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "d4091fa13491c158f65a4fd7f7e041f82453b23afe1366e5f32923775a78e5aa", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aad3898c344279cac58a6820a97d8440604865c9b471edd0420b33e19a7a3ac2", "generation_seconds_batch": 19.248196749016643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24319683015346527, "target_z": -0.35156250929541477, "ce": 6.022613525390625, "genuineness": 4.632867813110352, "identity": 0.6503790616989136, "hypothesis": "La porte 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_Disappointment/d4091fa13491c158f65a4fd7f7e041f82453b23afe1366e5f32923775a78e5aa.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "d432922f0ee757054c352698d7c296b28312e374d36b182315d7ac03049a0f0c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3316e0bc32da203d234bd945e00afc4b9af57941a96425826b4033f0751387b2", "generation_seconds_batch": 19.35028323403094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07060113549232483, "target_z": -0.597656246680209, "ce": 6.348263263702393, "genuineness": 4.720732688903809, "identity": 0.4661403298377991, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d432922f0ee757054c352698d7c296b28312e374d36b182315d7ac03049a0f0c.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "d444f007944fd40c296fac94857754e270e4e8bc9a4ed25c84380f4afe1f7f4d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "172692b2fabfacc5ef34246271d7474433d3571d75aa0efa82a6a9e976639576", "generation_seconds_batch": 19.836100550019182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08429920673370361, "target_z": -0.5781249973441672, "ce": 6.459460258483887, "genuineness": 4.6705241203308105, "identity": 0.5823583602905273, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie standen neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d444f007944fd40c296fac94857754e270e4e8bc9a4ed25c84380f4afe1f7f4d.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "d46d274faa66bc4cee1164baf08ad5f88b2c42505ad5be3d2ee547f4e8714dd8", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2fba85d0620d177afcab6457bb513f55339b2f44b5612410f13dd0c1ef4e2ec4", "generation_seconds_batch": 20.116676776087843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2226497232913971, "target_z": -0.3808593832994775, "ce": 6.197352409362793, "genuineness": 4.7332844734191895, "identity": 0.6567497253417969, "hypothesis": "Die Tür 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_Disappointment/d46d274faa66bc4cee1164baf08ad5f88b2c42505ad5be3d2ee547f4e8714dd8.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "d5b8bd35d35cefd096eb7c7ab7a287ea0e8090cf27c31dcd51edd74dee4925a8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "67e9fc5cbdc2bd28697fa0e34b42c9d28d2daf7718a8f5177a1380f59da20285", "generation_seconds_batch": 14.47174917603843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21854031085968018, "target_z": -0.3867187453522926, "ce": 6.141753673553467, "genuineness": 4.68307638168335, "identity": 0.6376784443855286, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d5b8bd35d35cefd096eb7c7ab7a287ea0e8090cf27c31dcd51edd74dee4925a8.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "d5c7f3d1321a0c62a9433b4f784663132e7e7d1ed93866c09f92e2dd8def1995", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "22e7af097146955295c5e10cbba8d58ad7fb5e3a88359c7a506db07afaf95a3c", "generation_seconds_batch": 18.941439741989598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27470239996910095, "target_z": -0.3066406273238537, "ce": 5.315715789794922, "genuineness": 4.7834930419921875, "identity": 0.8498631715774536, "hypothesis": "La porte 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_Disappointment/d5c7f3d1321a0c62a9433b4f784663132e7e7d1ed93866c09f92e2dd8def1995.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": "d6362034c22e31fe7b536475c3c7922f4848cf53c13539b2a2cf65e0137aa428", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "56022a3a9af383b98669328910e1719daac6965a672968dabf5b3a37d740c8fe", "generation_seconds_batch": 15.049087673891336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34593236446380615, "target_z": -0.20507813927510127, "ce": 5.752562999725342, "genuineness": 4.444586753845215, "identity": 0.6491172313690186, "hypothesis": "De sleutels liggen op de keukentafel. Ik kijk 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_Disappointment/d6362034c22e31fe7b536475c3c7922f4848cf53c13539b2a2cf65e0137aa428.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "d72074ba2ad704dd025450b4003d231af219650371dd7210d70aff1d068a49de", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "17bf6aae942cf433ffd1ad20c49222c0fc037b942c7e078682f51ddc94ab18da", "generation_seconds_batch": 21.402667595888488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1555291712284088, "target_z": -0.47656250929541477, "ce": 6.078212261199951, "genuineness": 4.68307638168335, "identity": 0.5870248079299927, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d72074ba2ad704dd025450b4003d231af219650371dd7210d70aff1d068a49de.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "d73fe618076b4f55fba5ca5285848b73fc34774b67d0f5e5555bd43197272305", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ba99504c0dae53785dc8e4083b3cf26464326023e440804b87accedc7cf402d1", "generation_seconds_batch": 22.60219835594762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13909149169921875, "target_z": -0.5, "ce": 6.141753673553467, "genuineness": 4.18726921081543, "identity": 0.5608681440353394, "hypothesis": "The 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_Disappointment/d73fe618076b4f55fba5ca5285848b73fc34774b67d0f5e5555bd43197272305.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": "d7442753e56a031d9e99929e5dbf6848583d6b911ec929d3dafe2f1b7ac4e0cd", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b00a0963c4395254cf4800d497ebcf886a63739072f9cfd340150f5420bce17f", "generation_seconds_batch": 14.871957016992383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24730625748634338, "target_z": -0.3457031259959373, "ce": 5.990842819213867, "genuineness": 4.413206577301025, "identity": 0.7252559661865234, "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_Disappointment/d7442753e56a031d9e99929e5dbf6848583d6b911ec929d3dafe2f1b7ac4e0cd.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "d74e41672488e867aa109343cb6f91f8b6ab1a1c3780e7efa03d22cc04c70fe6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "669d69261a42dd6b108c1edfbc56919e935c7edb47a32ef30931d6e144baf9e1", "generation_seconds_batch": 19.28015595697798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25963452458381653, "target_z": -0.3281249973441672, "ce": 6.23706579208374, "genuineness": 4.808597087860107, "identity": 0.490334689617157, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d74e41672488e867aa109343cb6f91f8b6ab1a1c3780e7efa03d22cc04c70fe6.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "d764d7518418ebaf8cb408998fe7f5de99b36ecf195286ccfc151f99c675c84e", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4a794b7c6c2bd408bb4a0a2c1dca4b4828040f07d4d56f6beff7d60dd88d206e", "generation_seconds_batch": 19.646597373997793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10347649455070496, "target_z": -0.5507812652710385, "ce": 5.692992687225342, "genuineness": 4.494794845581055, "identity": 0.7205547094345093, "hypothesis": "J'ai trouvé la 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_Disappointment/d764d7518418ebaf8cb408998fe7f5de99b36ecf195286ccfc151f99c675c84e.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": "d8281d0d5ca20807367f0865ae257c5434772016988b86b1cec315c29de06f0e", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7bdc912bbde9bde88c3b02f9ae79a60805fcb713139c38b72c19abab4eb78bd", "generation_seconds_batch": 14.480976433958858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9500173330307007, "target_z": 0.6562499946883344, "ce": 5.919358730316162, "genuineness": 4.482243061065674, "identity": 0.378878653049469, "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_Disappointment/d8281d0d5ca20807367f0865ae257c5434772016988b86b1cec315c29de06f0e.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "d82edd7f4341d85b7d8b25f357f0c63428ba5654063feeb5b663f63b2d1a230f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "544ceecd96e76c4284a895f7db914a3048214b0cd4288aebb1f1de5d0fc936fe", "generation_seconds_batch": 16.884379753959365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17196685075759888, "target_z": -0.45312501859082954, "ce": 6.086154937744141, "genuineness": 4.909013748168945, "identity": 0.8060692548751831, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d82edd7f4341d85b7d8b25f357f0c63428ba5654063feeb5b663f63b2d1a230f.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "d8487b848632f23a40260709bc2addfe1f1c53ed61e4f19332ded0ac4a8b4c57", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5aec57c381b8c1f109f982dc83682568e7926daf8d7893fd56f087e04f1ab431", "generation_seconds_batch": 19.913251132005826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1692272424697876, "target_z": -0.457031259959373, "ce": 5.919358730316162, "genuineness": 4.419482707977295, "identity": 0.4769406318664551, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d8487b848632f23a40260709bc2addfe1f1c53ed61e4f19332ded0ac4a8b4c57.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "d8c6763af9666e9f0eab4fd1b54af3c4dd17648d2bc8a78f0996633a3c468a54", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c63f7dd4f10e9657f3e7a66b2c27cde0e55cc56ad7e47f7c96326ab7f29e8c62", "generation_seconds_batch": 23.91424252500292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008847683668136597, "target_z": -0.7109375013279164, "ce": 6.292664527893066, "genuineness": 4.645420074462891, "identity": 0.5552339553833008, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d8c6763af9666e9f0eab4fd1b54af3c4dd17648d2bc8a78f0996633a3c468a54.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "d8cc2abdf381eddfc13932f1754da9dabc5b4bc604d5823636c9ff85d2037778", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c67751bc6ed10be22f55ca915247f5eeb1abdba9e5f411f71b2d0dc6708bb58b", "generation_seconds_batch": 19.456832692958415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41442275047302246, "target_z": -0.10742185010156755, "ce": 5.689021587371826, "genuineness": 4.6956281661987305, "identity": 0.5748691558837891, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d8cc2abdf381eddfc13932f1754da9dabc5b4bc604d5823636c9ff85d2037778.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "d8fe831edf7a57b04d852acfbb7fd9369de7f86ebf1cecaa61409763a946c4a5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0a2fe75d5e3a306324edabece861c2bb3dac973e18f838d96cf63bb3994f52ad", "generation_seconds_batch": 19.075813103001565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.103435754776001, "target_z": 0.8750000212466623, "ce": 5.927301406860352, "genuineness": 4.319066047668457, "identity": 0.6086068749427795, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d8fe831edf7a57b04d852acfbb7fd9369de7f86ebf1cecaa61409763a946c4a5.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "d95ac80ea7d31f378d52d1b0f78a2f6434ccb559659036597eaf8f9124789df3", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "04bdb4814f98fb6c4816e9e29e3d73c59c528d1b67437db1fd2fae13fb942c32", "generation_seconds_batch": 19.751192939002067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16511783003807068, "target_z": -0.4628906220121881, "ce": 6.260893821716309, "genuineness": 4.444586753845215, "identity": 0.33753660321235657, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d95ac80ea7d31f378d52d1b0f78a2f6434ccb559659036597eaf8f9124789df3.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": "d96ea1769464e84035974fabe848eb4fd5bdacb79e6bb699eac21e82aecedf88", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "00598b2c3c0cac17b3276029473dad3c53e42285e49719ca9b334a7c19ab1785", "generation_seconds_batch": 19.276680751005188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3623700737953186, "target_z": -0.18164060607719135, "ce": 5.780362129211426, "genuineness": 4.331617832183838, "identity": 0.6733814477920532, "hypothesis": "Ik schreef het nummer op de envelop, lees het goed en controleer de laatste twee cijfers. Wel me wanneer je even tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d96ea1769464e84035974fabe848eb4fd5bdacb79e6bb699eac21e82aecedf88.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "d9a1e3a250b69c9de74f3d902e4d305fa57410a502bf440fd5f269817a3c2540", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d5ad02ad73c9cbcbb188e4e42bca77019b3ff3547fba4c7192d90b4d4967bfc9", "generation_seconds_batch": 14.197147555998527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6246881484985352, "target_z": 0.19238283358067282, "ce": 5.585766792297363, "genuineness": 4.595211505889893, "identity": 0.4869118928909302, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/d9a1e3a250b69c9de74f3d902e4d305fa57410a502bf440fd5f269817a3c2540.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": "da6e8aac9e3bdc11ef6a6550ec485dbdca2d7d78203010298b442a917b0c742d", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a9b9776cb173561aa125d97c8fadb8f767a2afc6e4a12f299fb070de7a3de372", "generation_seconds_batch": 19.385573319043033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30346834659576416, "target_z": -0.2656250079674984, "ce": 5.831989288330078, "genuineness": 4.7081804275512695, "identity": 0.6716644763946533, "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_Disappointment/da6e8aac9e3bdc11ef6a6550ec485dbdca2d7d78203010298b442a917b0c742d.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "daa5496ce896cb6537666a308e99b10e344be43d0622fee6bd03283fa5310ecf", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e7f5340545aeffd457be618e55f6eb665b186ba58b0a8d20fffd3f8a3797773b", "generation_seconds_batch": 21.30608138302341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3377135396003723, "target_z": -0.2167968633807315, "ce": 5.990842819213867, "genuineness": 4.758388519287109, "identity": 0.8625048398971558, "hypothesis": "J'ai trouvé la 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_Disappointment/daa5496ce896cb6537666a308e99b10e344be43d0622fee6bd03283fa5310ecf.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "4798675ce4d87e3b47f10c4c8ac1cc89cbdf6ced80f143989b2e2af9abd7b1b3", "generation_seconds_batch": 14.309465100988746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 6.38797664642334, "genuineness": 4.268857479095459, "identity": 0.33344900608062744, "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_Disappointment/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.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": "db459de9785b566807adaabf231b2e0bf4a296d075c9a56434d1fe63cce9f955", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "128b24de85973b05f36b299e9e843a0d7e02a6f4b453234c7f7f9077da1deedc", "generation_seconds_batch": 19.404544097953476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22538933157920837, "target_z": -0.37695314193093404, "ce": 5.681078910827637, "genuineness": 4.632867813110352, "identity": 0.6285082101821899, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/db459de9785b566807adaabf231b2e0bf4a296d075c9a56434d1fe63cce9f955.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "dd02615d23ed7fa32c07a85246a00a9fc8ca0bf64a5d747ae06caa0a40f7d781", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "612d224ad73e3c3fd503ceba4abb5e452b8f716f568f5b5cdccab59e1d0ef2ce", "generation_seconds_batch": 19.182511113001965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12265381217002869, "target_z": -0.5234374907045852, "ce": 5.80021858215332, "genuineness": 4.432034492492676, "identity": 0.7331746816635132, "hypothesis": "J'ai trouvé la 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_Disappointment/dd02615d23ed7fa32c07a85246a00a9fc8ca0bf64a5d747ae06caa0a40f7d781.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "dd0dcf51d8d6ebd0f25e6a67feb65ea6e931fc843bfb68edd6765d8e78a83715", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "50e3bbfc1a74002d386edf42cb3f908e739ce9c02d8b1900a037f57ab6eac314", "generation_seconds_batch": 19.13963764999062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3185362219810486, "target_z": -0.24414063794718488, "ce": 6.133810997009277, "genuineness": 4.570107460021973, "identity": 0.5616961717605591, "hypothesis": "ik heb het kleine doosje gevonden het stond naast het oude raam we kunnen er samen in kijken", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/dd0dcf51d8d6ebd0f25e6a67feb65ea6e931fc843bfb68edd6765d8e78a83715.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "dd225650398c40607f867da4ffcda164ddf6ad96d67d960b0ea334dcdfbf2018", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33ffce13eae48ab3d1b96d036c598f8d88690f00c9c45eda69d3288d50eb962f", "generation_seconds_batch": 20.94831195799634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23223838210105896, "target_z": -0.3671874960162508, "ce": 6.006728172302246, "genuineness": 4.6705241203308105, "identity": 0.5442670583724976, "hypothesis": "Ma porte est encore ouverte. J'ai j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/dd225650398c40607f867da4ffcda164ddf6ad96d67d960b0ea334dcdfbf2018.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "dd44644c215263805989f4957b03268ef7d69f4eef0952c9bea32e4094126763", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2bb35bd8a21c20e6a5f7a36e45218be2e1e18639616a5c120b7efc03a9930d0f", "generation_seconds_batch": 19.55948807299137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7116708755493164, "target_z": 0.31640623074521224, "ce": 5.990842819213867, "genuineness": 4.425758361816406, "identity": 0.4451753497123718, "hypothesis": "Ik 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_Disappointment/dd44644c215263805989f4957b03268ef7d69f4eef0952c9bea32e4094126763.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": "dd6e1d4f10f7265fcc6ca9767b17a7fde466e9eaccd10a5a570c2e498e6e4f0a", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "728ca49b812c7e92c79a481e80cf952704621df197dab9e1ed44a62b193e721a", "generation_seconds_batch": 15.131064251996577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33908334374427795, "target_z": -0.2148437426964598, "ce": 5.617537498474121, "genuineness": 4.425758361816406, "identity": 0.8027912974357605, "hypothesis": "J'ai écrit le le numéro sur l'enveloppe, les biens, et vérifié les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.22727272727272727, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/dd6e1d4f10f7265fcc6ca9767b17a7fde466e9eaccd10a5a570c2e498e6e4f0a.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "ddb21a99cc3dbe574646ea15b3d0fac358fe26603897e20defd3cb22e2bb680d", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0372e6cc0d122da4f4881bfcbe97e3fadd6a40eca02d0b54418588a1e0e0dd64", "generation_seconds_batch": 14.940915031940676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10347649455070496, "target_z": -0.5507812652710385, "ce": 6.372091293334961, "genuineness": 4.632867813110352, "identity": 0.4236648976802826, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ddb21a99cc3dbe574646ea15b3d0fac358fe26603897e20defd3cb22e2bb680d.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "ddc0742bf7a5d6b83f36a230a8ba65e11ec492a9152ae40a8f46c796807032e5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "da04b170ac99612ff24d8878c6c9c72cf074c07a906a25c7a9abcc7becfda2d3", "generation_seconds_batch": 22.640669084037654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4308604300022125, "target_z": -0.08398435939698233, "ce": 5.561938762664795, "genuineness": 4.7332844734191895, "identity": 0.4981904625892639, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ddc0742bf7a5d6b83f36a230a8ba65e11ec492a9152ae40a8f46c796807032e5.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": "dde5d65c07ed2185c928dfb99681cf354c477dcfd842eff3b99296d7586ec517", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61985040947817416e3f693294910bac954c82a7908d3de11d093002015aadee", "generation_seconds_batch": 22.721658042049967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22949877381324768, "target_z": -0.37109373738479423, "ce": 5.542081832885742, "genuineness": 4.432034492492676, "identity": 0.4162648916244507, "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_Disappointment/dde5d65c07ed2185c928dfb99681cf354c477dcfd842eff3b99296d7586ec517.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "de2a5e830a4212370fa6c9d291c9064386cc02c20a444d996d055e10da5da963", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c13f87c288a7522654fff4d4b839f2f0398d7dfd666f5b29722f6472d3d36b5e", "generation_seconds_batch": 14.19633239810355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6678370237350464, "target_z": 0.2539061988752187, "ce": 5.371314525604248, "genuineness": 4.494794845581055, "identity": 0.8067787885665894, "hypothesis": "J'ai trouvé la 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_Disappointment/de2a5e830a4212370fa6c9d291c9064386cc02c20a444d996d055e10da5da963.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": "debf5baf0f0963d19278226aec8db6d093b7c5aa1dc3d4194c99517d8379e03c", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ad5159d8bfed33fd2abb3cb191cf589a46ac5afa6e05acc37c69ed5f160e7ad8", "generation_seconds_batch": 19.352830540039577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2966192960739136, "target_z": -0.27539065388218165, "ce": 5.708878040313721, "genuineness": 4.570107460021973, "identity": 0.6838127374649048, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería. La colocaremos después de comer.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/debf5baf0f0963d19278226aec8db6d093b7c5aa1dc3d4194c99517d8379e03c.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "df1f2d4e5b8eb49e16f873707e80ac349f0bdba7d417202a67d4e8949d3d70a8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "abb470df93291d43d6cbba37034ec76d23ff4a6c048834e709a72cc003c71acd", "generation_seconds_batch": 19.27418991003651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11991420388221741, "target_z": -0.5273437320731287, "ce": 6.221180438995361, "genuineness": 4.68307638168335, "identity": 0.3674777150154114, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/df1f2d4e5b8eb49e16f873707e80ac349f0bdba7d417202a67d4e8949d3d70a8.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "df25b1a43374e1b56ec76458b81db453e80359bc16db1843ff8af1956c626a1b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "00845b29f3694743cb58b02ea64f0914601cded897f0b9f094cb16d8b0b9f633", "generation_seconds_batch": 15.410941771930084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15278956294059753, "target_z": -0.4804687506639582, "ce": 6.181467056274414, "genuineness": 4.293961524963379, "identity": 0.5203855037689209, "hypothesis": "The 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_Disappointment/df25b1a43374e1b56ec76458b81db453e80359bc16db1843ff8af1956c626a1b.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "df543910c9a4771a4fe524fafe3904d0a8d8419bb3a3968d3ac4edd2b5d9a55c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "565dcdcaede349d5098ad5eb8df0d383f89a7c0b4a7c823ec27c3373dc76d9eb", "generation_seconds_batch": 19.277462960919365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3541512191295624, "target_z": -0.1933593726761463, "ce": 5.736677646636963, "genuineness": 4.758388519287109, "identity": 0.7405766248703003, "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_Disappointment/df543910c9a4771a4fe524fafe3904d0a8d8419bb3a3968d3ac4edd2b5d9a55c.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "df5b8ee93356fdeda985f882e39eb373ad6493fa35e3e9ea8535b5b5c946522b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "02dc53476f159f0058d330ff0d54f2fce2df839900dce6adc1a5fa723c987c60", "generation_seconds_batch": 20.399821860948578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32401543855667114, "target_z": -0.23632815521009803, "ce": 6.213237762451172, "genuineness": 4.758388519287109, "identity": 0.6475061178207397, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/df5b8ee93356fdeda985f882e39eb373ad6493fa35e3e9ea8535b5b5c946522b.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "df809c1342668c65d1ab2b2191250bb49f2b3baec09d72b8fcafeae863ff72c9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d28f2d0670ee2ee4b097c4ee303879ddc4153a96b41973b1a57b6981f7da23b4", "generation_seconds_batch": 20.60035069694277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2116912603378296, "target_z": -0.3964843912669759, "ce": 5.974957466125488, "genuineness": 4.2249250411987305, "identity": 0.5742193460464478, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/df809c1342668c65d1ab2b2191250bb49f2b3baec09d72b8fcafeae863ff72c9.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": "dfe058c5e8ac56973ebbe9aa4bedeb35f83938c6e3bfefce67826471b773ea5c", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51c2da995e926b989daf732103fd9e0a6aebed5928fd190e43acbbf879fe2b6a", "generation_seconds_batch": 15.24554731999524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0650811195373535, "target_z": 0.8203124721137557, "ce": 5.363371849060059, "genuineness": 4.532451152801514, "identity": 0.557060718536377, "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_Disappointment/dfe058c5e8ac56973ebbe9aa4bedeb35f83938c6e3bfefce67826471b773ea5c.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "dffd1087c6886ab247438d7926fc5507787468cbe84ea6a5c068aeccaf4f1a4b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b4f53572eed0fb99c785950c67a343fd40c6ad20dad1ff50f3385d83ada08100", "generation_seconds_batch": 19.304013716988266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1979931890964508, "target_z": -0.41601564060301766, "ce": 6.173524379730225, "genuineness": 4.319066047668457, "identity": 0.2820883095264435, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/dffd1087c6886ab247438d7926fc5507787468cbe84ea6a5c068aeccaf4f1a4b.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "e00232350444e649c238946188dae3f56137f6f722e27c2c8b9d0fa2e69a9b8c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ab14154f7790618f97bc37252fbb35768d9f906021560eac737a1e1283b4207e", "generation_seconds_batch": 22.17689439491369, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5144186615943909, "target_z": 0.03515625730354019, "ce": 5.764476776123047, "genuineness": 4.758388519287109, "identity": 0.6848515272140503, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e00232350444e649c238946188dae3f56137f6f722e27c2c8b9d0fa2e69a9b8c.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": "e04a0fc351376b13137d98fd2538c11bd5ae503d745ba1c2c73ab8b2e7d5fece", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b34cce14cc3c3d65942ddb3306aeffffbefda7ede41a3bd8264667db7cd7d1fa", "generation_seconds_batch": 19.206959026982076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47058483958244324, "target_z": -0.02734373207312863, "ce": 5.609594821929932, "genuineness": 4.570107460021973, "identity": 0.5013293623924255, "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_Disappointment/e04a0fc351376b13137d98fd2538c11bd5ae503d745ba1c2c73ab8b2e7d5fece.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "e06c5aff58c514a5e4a2a09ce4d90d7a9be1de7fdb60c28843a8e320b03790f2", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "69587f11a09e1f22622708598df04b7f59e25bed54a4db66560ac0a86d94d734", "generation_seconds_batch": 14.299811575911008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21443089842796326, "target_z": -0.39257810740510773, "ce": 5.903473377227783, "genuineness": 4.507347106933594, "identity": 0.4319925904273987, "hypothesis": "The 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_Disappointment/e06c5aff58c514a5e4a2a09ce4d90d7a9be1de7fdb60c28843a8e320b03790f2.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": "e08d2f032560dc43a8dbe2213b493a3738c318d3c54c1cc91f850e4399ff59c2", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "06d3f2c13862ffdc47f978d65e93e98a7a2d0bbdcd273948c5c7836a4ea600c7", "generation_seconds_batch": 14.60922791203484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39935484528541565, "target_z": -0.12890626261520577, "ce": 5.689021587371826, "genuineness": 4.432034492492676, "identity": 0.6442066431045532, "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_Disappointment/e08d2f032560dc43a8dbe2213b493a3738c318d3c54c1cc91f850e4399ff59c2.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": "e0ac6d32161486c9e3e8ca43489fe67e4d931acbbe302d621eec4d6175dcea4b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68510db3628bf3429dea69e62c02e2830aac2a9c264ea82f6debbe695b4759b2", "generation_seconds_batch": 14.799191789003089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2719627916812897, "target_z": -0.3105468686923971, "ce": 5.685050010681152, "genuineness": 4.406930446624756, "identity": 0.5471984148025513, "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_Disappointment/e0ac6d32161486c9e3e8ca43489fe67e4d931acbbe302d621eec4d6175dcea4b.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "e146c32726caf88c78a6f67bcf1abe38ac979160a613d25deb060161b08caa4b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fc55a46c38b3cc2c07cfbfef0c22ea34634aa80a3f3b37bb1ffd4b1979d9cc50", "generation_seconds_batch": 19.359982753987424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04320499300956726, "target_z": -0.6367187453522926, "ce": 6.372091293334961, "genuineness": 4.444586753845215, "identity": 0.1960354745388031, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e146c32726caf88c78a6f67bcf1abe38ac979160a613d25deb060161b08caa4b.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "e1627906e8de5e6f66638ad808e0f9e8852c220bd9362c15e8f99db50d826310", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1d23288058e383e52df7f1a76fa9cb03aa6d80356c6ad3ac54f0490de567d538", "generation_seconds_batch": 19.292222357937135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2226497232913971, "target_z": -0.3808593832994775, "ce": 5.6532793045043945, "genuineness": 4.6203155517578125, "identity": 0.5977864265441895, "hypothesis": "La porte 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_Disappointment/e1627906e8de5e6f66638ad808e0f9e8852c220bd9362c15e8f99db50d826310.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "e1a397a42407a3f97038160df08a01121235c93425f6a9f7cce5cacf7609d520", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5559a8d2da4f8369b1abe763a56363a8846aaec9cad8b21d7d01e49ddc9056d1", "generation_seconds_batch": 19.182511113001965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14320090413093567, "target_z": -0.4941406379471849, "ce": 5.895530700683594, "genuineness": 4.632867813110352, "identity": 0.7598239183425903, "hypothesis": "J'ai trouvé la petite boîte elle était près de de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e1a397a42407a3f97038160df08a01121235c93425f6a9f7cce5cacf7609d520.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "e1b50f249828bc2cdb9ec05b2c28342574dae5c6599dd2200ad96ddbce849168", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4f1ea2a029686377e08cb83862375933a7068546f92377274b985a0472c30db6", "generation_seconds_batch": 16.67572555609513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9828927516937256, "target_z": 0.7031250610841543, "ce": 5.967014789581299, "genuineness": 4.595211505889893, "identity": 0.31778788566589355, "hypothesis": "De deur 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_Disappointment/e1b50f249828bc2cdb9ec05b2c28342574dae5c6599dd2200ad96ddbce849168.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "e21befa1848061685110a722913a7a3d7028dba2505a1ea29c0375a05fb71074", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9fdfc17c5367181acc714a5631d7cedbdd77e75563c51b3143d9d28de7968e66", "generation_seconds_batch": 19.53927271196153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22812896966934204, "target_z": -0.37304685806906596, "ce": 5.732706069946289, "genuineness": 4.909013748168945, "identity": 0.4978363811969757, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e21befa1848061685110a722913a7a3d7028dba2505a1ea29c0375a05fb71074.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "e2413eaf2cc50118ac7c495bd43f8cc9be72f47468b7280ed44e3e1e16a1d31b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4462941b41121dc83822f70406a54b3731860a7b485e671d6248ec858d504515", "generation_seconds_batch": 18.941439741989598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37058889865875244, "target_z": -0.16992188197156108, "ce": 5.879645347595215, "genuineness": 4.6203155517578125, "identity": 0.7608205676078796, "hypothesis": "La porte est encore ouverte. J'ai poussé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e2413eaf2cc50118ac7c495bd43f8cc9be72f47468b7280ed44e3e1e16a1d31b.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "e32f30c7b899747771f7aecc308e4ed26cee53113d03a97f0add2a72df486e42", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fa2634687b2e52adf023b2e8efbef2c87845711897e7e0f32ac2d54c04f620ee", "generation_seconds_batch": 16.600425380980596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4719546437263489, "target_z": -0.025390611388856923, "ce": 6.260893821716309, "genuineness": 4.796044826507568, "identity": 0.6389681100845337, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e32f30c7b899747771f7aecc308e4ed26cee53113d03a97f0add2a72df486e42.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "e3f817534ecf0aa772e642917ac0f68ef04373579d6a332e235443c07459aba9", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bfc55c197dcea94db3701271d12e045e3ee63fcb99303dd687fd54211f981a0e", "generation_seconds_batch": 19.425936658051796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1582687795162201, "target_z": -0.4726562679268714, "ce": 5.998785495758057, "genuineness": 4.7081804275512695, "identity": 0.6809136867523193, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e3f817534ecf0aa772e642917ac0f68ef04373579d6a332e235443c07459aba9.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "e5ba2d9296ec39b8b4f31a60f85f73c97c59085b2963ba99f1e2f4589f449a47", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ed947cb7c624b8f9a15a2f1d49b8d6f9b703343e4a5afd4ec345756af8dc3d73", "generation_seconds_batch": 20.01673187792767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2760722041130066, "target_z": -0.304687506639582, "ce": 5.689021587371826, "genuineness": 4.7834930419921875, "identity": 0.7772915959358215, "hypothesis": "La porte 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_Disappointment/e5ba2d9296ec39b8b4f31a60f85f73c97c59085b2963ba99f1e2f4589f449a47.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "e5c2dcdb3eeac99795afad5037235e48a93a4b0ed6dafdd00d446399254ba81c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cd5e026751771f39b7acaf52293aef9f46560ae02a29de6c200163235f4bc4fc", "generation_seconds_batch": 15.352958665927872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06786152720451355, "target_z": -0.6015624880487525, "ce": 6.292664527893066, "genuineness": 4.65797233581543, "identity": 0.3485489785671234, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e5c2dcdb3eeac99795afad5037235e48a93a4b0ed6dafdd00d446399254ba81c.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "e5de19711383a22efaffdf1ebb6181bc7fa545b9f8931edaca13219b7a576d76", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "31cec4a6da4b9c9161e16e5741c667e9ab4b6aece631b2ea28332fe4681e03a6", "generation_seconds_batch": 22.526097730966285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43496984243392944, "target_z": -0.07812499734416721, "ce": 5.756534099578857, "genuineness": 4.6203155517578125, "identity": 0.5501033067703247, "hypothesis": "J'ai trouvé la 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_Disappointment/e5de19711383a22efaffdf1ebb6181bc7fa545b9f8931edaca13219b7a576d76.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "e5f259d5159105ec920224e7a0096ce61e04ca5fdb1b66a91a40d4d1b50c49c5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "db3342ca291edd6b1ff32468354c327ce0ac6c39b5f2a0a7357a8cd4d11fcf2f", "generation_seconds_batch": 21.96375277696643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2541552782058716, "target_z": -0.33593752257457876, "ce": 5.77639102935791, "genuineness": 4.545003414154053, "identity": 0.5366525053977966, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e5f259d5159105ec920224e7a0096ce61e04ca5fdb1b66a91a40d4d1b50c49c5.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "e68b40bee737a799daeba4904ba3caca81b9122b21c7844284277adf298763e1", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9f54028f8bf670df5f353146646121b7283ede29bb4851d7c74e907cff214039", "generation_seconds_batch": 14.438800552976318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6144145727157593, "target_z": 0.17773436470864792, "ce": 5.808161735534668, "genuineness": 4.6203155517578125, "identity": 0.20797935128211975, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e68b40bee737a799daeba4904ba3caca81b9122b21c7844284277adf298763e1.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "e68c9ce34d3675aa09383e2355f96785c1813cec8c33b483334d7eccdf6af45d", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f69a361b87f7dd11e58b49687d0b2adfba84f177ebfee8900213dc4ad81949b1", "generation_seconds_batch": 15.737292825011536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32812488079071045, "target_z": -0.2304687506639582, "ce": 6.054384231567383, "genuineness": 4.432034492492676, "identity": 0.5566285848617554, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e68c9ce34d3675aa09383e2355f96785c1813cec8c33b483334d7eccdf6af45d.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": "e69afaa9d89112aa63e6edc676dba24e96ba3fa8c5784c572c36328e406ebc8b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "879b9db623e7847f4985b8cac9ed13baf8f68b893fe6031b10add213f5cbd745", "generation_seconds_batch": 15.634378265938722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25278550386428833, "target_z": -0.33789060076552574, "ce": 6.078212261199951, "genuineness": 4.381826400756836, "identity": 0.4160052537918091, "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_Disappointment/e69afaa9d89112aa63e6edc676dba24e96ba3fa8c5784c572c36328e406ebc8b.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "2cede53f640a0325326cbabb58f77001a776eb657d824fe1269c7635cf875850", "generation_seconds_batch": 14.553182182018645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21443089842796326, "target_z": -0.39257810740510773, "ce": 6.348263263702393, "genuineness": 4.231201171875, "identity": 0.6846618056297302, "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_Disappointment/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "e776409af795879bae2eec0791df579cfd2d9d26ae0673a12e5ece1276a3042f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9e947b935e03dcc832617cd084b2f9888d025490ec02e7cb6467736958fc7840", "generation_seconds_batch": 19.459415694931522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14320090413093567, "target_z": -0.4941406379471849, "ce": 6.157639026641846, "genuineness": 4.7834930419921875, "identity": 0.765295147895813, "hypothesis": "J'ai trouvé la 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_Disappointment/e776409af795879bae2eec0791df579cfd2d9d26ae0673a12e5ece1276a3042f.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "e87109d9edd2b673ca0ac311b53db22b5ae749483ea7ecd19660b20b98233c72", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bbcbbdd92ef18dbb5fdcb0b925d0235686e697435b108ad3a70ed9658536cd8e", "generation_seconds_batch": 19.75363880605437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2555251121520996, "target_z": -0.33398435939698234, "ce": 5.7247633934021, "genuineness": 4.833701133728027, "identity": 0.6281268000602722, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e87109d9edd2b673ca0ac311b53db22b5ae749483ea7ecd19660b20b98233c72.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "e88066d8f4052d6e182f47d509f1a3f4d9ebb04149547007cd63843d1d991db7", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1ca60f61e8896b115ac96c803bbe3d22d999048d010b5c4737a1387da1ccfcc4", "generation_seconds_batch": 19.24692635401152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.569210946559906, "target_z": 0.11328125464770739, "ce": 5.689021587371826, "genuineness": 4.7081804275512695, "identity": 0.7869866490364075, "hypothesis": "J'ai trouvé la 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_Disappointment/e88066d8f4052d6e182f47d509f1a3f4d9ebb04149547007cd63843d1d991db7.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "e8c1742d002622a8f8f0bbb5cfc6afe41c17ffb9adc7f9c227a04a774f5d6904", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "df076d92fe7d7bba1c08512557083fd216bbb25f15c48e060c7eb900e225b5a0", "generation_seconds_batch": 19.139526894898154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2226497232913971, "target_z": -0.3808593832994775, "ce": 5.903473377227783, "genuineness": 4.519899368286133, "identity": 0.2554253935813904, "hypothesis": "The 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_Disappointment/e8c1742d002622a8f8f0bbb5cfc6afe41c17ffb9adc7f9c227a04a774f5d6904.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "e8dced212e7a859bb75b78642c011f700c91a2ae5eb40643e8946d0d77302446", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2ea1420b17b4e5299a0dc198c5dd3615bf127a4fcc801c7d79499fd680ddc230", "generation_seconds_batch": 19.043710296973586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33908334374427795, "target_z": -0.2148437426964598, "ce": 5.514282703399658, "genuineness": 4.519899368286133, "identity": 0.5808630585670471, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e8dced212e7a859bb75b78642c011f700c91a2ae5eb40643e8946d0d77302446.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "e98be9f3acb2dda953715df49937ff3b24b1ca74ff4c0f6b51a92309981356f4", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cf84a7062cd9ac1452637348109239275dd2cdde4ae47332756e2c08ce52fcab", "generation_seconds_batch": 15.99763045203872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.056903064250946045, "target_z": -0.6171874960162508, "ce": 6.284721851348877, "genuineness": 4.507347106933594, "identity": 0.30148011445999146, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/e98be9f3acb2dda953715df49937ff3b24b1ca74ff4c0f6b51a92309981356f4.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "838ef53413a49b1101f9158f97d093e63beadfb1739fb8a6d9b5d367e25dc36b", "generation_seconds_batch": 14.951194775057957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0979972779750824, "target_z": -0.5585937480081254, "ce": 6.483288764953613, "genuineness": 4.3881025314331055, "identity": 0.47485101222991943, "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_Disappointment/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.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": "ea364d12110eaa8c3c858ed5a859e4321443160253f40974b5640e4dfe44d084", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28564144f9b1ee989436c9f33299a313f85aa67bb35c63f1461ba5c7ad8597b5", "generation_seconds_batch": 22.721658042049967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25004586577415466, "target_z": -0.3417968846273939, "ce": 5.871703147888184, "genuineness": 4.7081804275512695, "identity": 0.617956280708313, "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_Disappointment/ea364d12110eaa8c3c858ed5a859e4321443160253f40974b5640e4dfe44d084.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "ea735b8cdadfb82d201765867f1bbc88da122f7cf98d7da2162956228fbfa520", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "54561003892e2c1a0cba698ea7cb47c7604ca7809bc3fce583e9f17837bc5cdf", "generation_seconds_batch": 14.415339317987673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07334074378013611, "target_z": -0.5937500053116656, "ce": 6.395919322967529, "genuineness": 4.65797233581543, "identity": 0.49537840485572815, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ea735b8cdadfb82d201765867f1bbc88da122f7cf98d7da2162956228fbfa520.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "ea90d28f77c85f3fa61ed012d3f2c65cbe0cb2366f773f11e80ee42aac5ef496", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "88ecea41772d126000ce8399de6de989b15f9b02522169efecb807cf8f26d608", "generation_seconds_batch": 21.729358191019855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17881590127944946, "target_z": -0.4433593726761463, "ce": 6.149696350097656, "genuineness": 4.432034492492676, "identity": 0.39412060379981995, "hypothesis": "The 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_Disappointment/ea90d28f77c85f3fa61ed012d3f2c65cbe0cb2366f773f11e80ee42aac5ef496.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "eaabcdc11ac24db5c14c3022db730a12811429eb480454b8863e7bc7c8f7c139", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d8fc26469337cfa789052f2ce0e7165a51ca3b10ad26a30dd6fffff23b4364cf", "generation_seconds_batch": 19.3636993879918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1336122751235962, "target_z": -0.5078124827370868, "ce": 5.982900142669678, "genuineness": 4.821148872375488, "identity": 0.6626111268997192, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/eaabcdc11ac24db5c14c3022db730a12811429eb480454b8863e7bc7c8f7c139.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "eb5b079e20b6d41dc8bdaf1eeef75951d5cfa0993d0b3aa3bfd1f1f45b7e7988", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c0b3d5458c038d7d6b62c5add5f544f1974b70c1eb396593f65bab035c27efa8", "generation_seconds_batch": 16.67572555609513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9554965496063232, "target_z": 0.6640624774254212, "ce": 5.542081832885742, "genuineness": 4.344170093536377, "identity": 0.29226329922676086, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/eb5b079e20b6d41dc8bdaf1eeef75951d5cfa0993d0b3aa3bfd1f1f45b7e7988.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "ebd013ab2f7f3c6c894daf6e9f08b13be719415a34d44d477b27ffd6b047a0f0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9b2c8af4c17a148efeecfb1be971b226d0e437bf0182fa1a153b325d61075434", "generation_seconds_batch": 14.327234541997313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30346834659576416, "target_z": -0.2656250079674984, "ce": 5.927301406860352, "genuineness": 4.758388519287109, "identity": 0.6412903070449829, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ebd013ab2f7f3c6c894daf6e9f08b13be719415a34d44d477b27ffd6b047a0f0.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "634e01a57eb005fd3eeb3a8dbc857b6eed5ecd5286f7785ea0ee972e1f5c678a", "generation_seconds_batch": 14.479995705070905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27470239996910095, "target_z": -0.3066406273238537, "ce": 6.109982967376709, "genuineness": 4.469690799713135, "identity": 0.8119574189186096, "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_Disappointment/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.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": "ebf08a9655c06235bde50003e86dc643ae26f51f3d55a3c06e6a05c1b58e31a2", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59418ca916132bdd6fc9caff963442f35126b5d5a1691a5325bc9fc44697f95e", "generation_seconds_batch": 15.63191532692872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23223838210105896, "target_z": -0.3671874960162508, "ce": 5.808161735534668, "genuineness": 4.68307638168335, "identity": 0.3442615866661072, "hypothesis": "The keys are on the kitchen table. I check the drawer, then look beside the window. Take them with you when you leave.", "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_Disappointment/ebf08a9655c06235bde50003e86dc643ae26f51f3d55a3c06e6a05c1b58e31a2.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "ec51d2af552e5d8249659a1dc130a74a6fce75e8c0c09c4f9a3a8fd0770bef92", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3ca1adf0af9ab0129c176a7356a6142cb20ac3cba98e15ca87598eb472dc2a27", "generation_seconds_batch": 23.013349346001633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.313057005405426, "target_z": -0.2519531206842717, "ce": 5.704906940460205, "genuineness": 4.7332844734191895, "identity": 0.777090847492218, "hypothesis": "La porte 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_Disappointment/ec51d2af552e5d8249659a1dc130a74a6fce75e8c0c09c4f9a3a8fd0770bef92.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "ec7aac2fc73412d31b8ff06ab7146fa7614e5f40da7a3bf92677ef4fb96b2e0b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8457ccea05a4fac92aaddf16fa0e37b5ae99a0a9bb4e20e5b949d06e6f2032e0", "generation_seconds_batch": 19.333276877063327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10621613264083862, "target_z": -0.5468749814091705, "ce": 6.141753673553467, "genuineness": 4.720732688903809, "identity": 0.6517335176467896, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ec7aac2fc73412d31b8ff06ab7146fa7614e5f40da7a3bf92677ef4fb96b2e0b.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "ed9b8bb6d6582814c12871b618f07452b0b838bd727ced9d2b884a01633273f4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6f938abcf3c2d64df3f00fe186a690d9d8a8347e24c277aad5f1ae40a2d86982", "generation_seconds_batch": 14.319756273995154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46784520149230957, "target_z": -0.031250015934996773, "ce": 5.331601142883301, "genuineness": 4.457139015197754, "identity": 0.45848628878593445, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ed9b8bb6d6582814c12871b618f07452b0b838bd727ced9d2b884a01633273f4.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "ee128366f0bac25c289c8bc922d81a88ddddf7265e4266283306031d762044d0", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "11535280ccf444c8ae06a960773bcb4a7d60620b2b5a826495f0f68875a5491e", "generation_seconds_batch": 19.303866153932177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23634779453277588, "target_z": -0.36132813396343566, "ce": 5.9431867599487305, "genuineness": 4.532451152801514, "identity": 0.4246925711631775, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ee128366f0bac25c289c8bc922d81a88ddddf7265e4266283306031d762044d0.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "ee3fc94efee12a90248af9a3fff1f0a657d688dcef0d99b5418fc422c1546d61", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fa1bd546d176d625fc5b15e1051ddae5e0f90a0e4cd93238447a295328b85436", "generation_seconds_batch": 19.887360075954348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21032145619392395, "target_z": -0.3984375119512476, "ce": 6.062326908111572, "genuineness": 4.570107460021973, "identity": 0.6437209844589233, "hypothesis": "La porte 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_Disappointment/ee3fc94efee12a90248af9a3fff1f0a657d688dcef0d99b5418fc422c1546d61.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "eeed5e1bb8c2536f9326ab85ce10b5a377f5586deb44cd96b702127be4da4111", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "706062b2dce1f52da587c31183245d468a8eae8f0240ca7b1031a795ee75dedd", "generation_seconds_batch": 20.641013584914617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1514197587966919, "target_z": -0.4824218713482299, "ce": 6.0305562019348145, "genuineness": 4.457139015197754, "identity": 0.4934546649456024, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/eeed5e1bb8c2536f9326ab85ce10b5a377f5586deb44cd96b702127be4da4111.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "eef1c6e65a4f8955f73796ada954b911e68ae7d2f9d148f2c230c82051c642e5", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3bc82f55b5d0577b66f37c7c8632299610f7638ecb9675e2370ffef01d88e4a0", "generation_seconds_batch": 22.336280976072885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21443089842796326, "target_z": -0.39257810740510773, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.6510095596313477, "hypothesis": "La porte 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_Disappointment/eef1c6e65a4f8955f73796ada954b911e68ae7d2f9d148f2c230c82051c642e5.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "ef0a68dc7d08fb6fc14b8c5751fe7734e3dd576b11240f2c70a1c0c05c24c67b", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "be1e871ea0e83b801a6ec2a70c68f7c0e784efeb85354b28c446cf1afe873337", "generation_seconds_batch": 22.75193816598039, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1938837766647339, "target_z": -0.4218750026558328, "ce": 6.24500846862793, "genuineness": 4.105680465698242, "identity": 0.15805873274803162, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ef0a68dc7d08fb6fc14b8c5751fe7734e3dd576b11240f2c70a1c0c05c24c67b.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "ef3c4a5595240f3bc0e87a9ba1042a170740ae41767de82668dba21f7a5203c6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "37dcf5bfbcf34110d8eccf1f957b0b206a6b3bec4367fbcdeaa1e7f8372482d8", "generation_seconds_batch": 14.532412442960776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17881590127944946, "target_z": -0.4433593726761463, "ce": 6.062326908111572, "genuineness": 4.883909225463867, "identity": 0.7035279273986816, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ef3c4a5595240f3bc0e87a9ba1042a170740ae41767de82668dba21f7a5203c6.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": "ef5e5ed156a7d83c1590b1b212223e1afe0e70ab5212802145562fb18228c324", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fc7fcd7d527d6ec1b03dd04f46ad0438904da403bc4b7904b553c73af5da9ff4", "generation_seconds_batch": 19.376421839930117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4377094507217407, "target_z": -0.07421875597562379, "ce": 5.5659098625183105, "genuineness": 4.369274139404297, "identity": 0.2756113111972809, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder. Tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ef5e5ed156a7d83c1590b1b212223e1afe0e70ab5212802145562fb18228c324.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "efd20198bba0acd7c6688e251ab03cb1af7fb061b05f2c22b454fcba707f7be4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "439e89164d4ea014920ac8e6f064509268d84b2a65c01c62b5120a999287eea1", "generation_seconds_batch": 14.929536634939723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5801693797111511, "target_z": 0.12890622012188105, "ce": 6.1894097328186035, "genuineness": 4.231201171875, "identity": 0.5411107540130615, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/efd20198bba0acd7c6688e251ab03cb1af7fb061b05f2c22b454fcba707f7be4.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "eff89e136e614faffbbaa4aa4f0ba903a7278305024b1d3b207b9e9f53459fb4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f58f9df29a51cd8db57e9f05c13194c2dfb6eab898b37a12f6c5c641c885122e", "generation_seconds_batch": 15.560155040002428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4466131925582886, "target_z": -0.061523450281195324, "ce": 6.157639026641846, "genuineness": 4.595211505889893, "identity": 0.27757424116134644, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/eff89e136e614faffbbaa4aa4f0ba903a7278305024b1d3b207b9e9f53459fb4.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "f0ca8ab599853f5eb7684601f33926f8a02c9e3486cb741d21fd4a55aa5862fe", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dc7b5378f4b4132cc756152400a02cec30fd91c949bcbd4152f60964ad67394b", "generation_seconds_batch": 15.660503581049852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28155142068862915, "target_z": -0.29687502390249515, "ce": 5.645336627960205, "genuineness": 4.821148872375488, "identity": 0.7350807189941406, "hypothesis": "La porte 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_Disappointment/f0ca8ab599853f5eb7684601f33926f8a02c9e3486cb741d21fd4a55aa5862fe.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": "f0f38057bee0e7fb023e8c3f1175182154bceaba744878674cc0e7ded385c7f3", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "408cb0bfd99ec0b5eea909604ecc60b28889f5f47d6959e059e66f5cce740a94", "generation_seconds_batch": 15.654443441075273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2760722041130066, "target_z": -0.304687506639582, "ce": 5.510311126708984, "genuineness": 4.3881025314331055, "identity": 0.524786114692688, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f0f38057bee0e7fb023e8c3f1175182154bceaba744878674cc0e7ded385c7f3.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "f0fb3dde3d90f149dbb8963f647bee249e0e4341a8e2a42d62e49a5534da2a0a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7329088cfa56edc8ff13e661f3b8cda4b73a9eaa901e5a5688f5ef99dc447413", "generation_seconds_batch": 19.77196899894625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18977436423301697, "target_z": -0.4277343647086479, "ce": 6.078212261199951, "genuineness": 4.7081804275512695, "identity": 0.5516718626022339, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f0fb3dde3d90f149dbb8963f647bee249e0e4341a8e2a42d62e49a5534da2a0a.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": "f1519b4465382ce2fcd53ee2c7bb2bfa941dcd1a955cca9c6c21a67a52e21f36", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c5f07978f2155c80a307a278f618df8190e1e30dcb849b82a181218c5cd604b0", "generation_seconds_batch": 19.276680751005188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4089435040950775, "target_z": -0.1152343753319791, "ce": 5.744620323181152, "genuineness": 4.306513786315918, "identity": 0.4784204363822937, "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_Disappointment/f1519b4465382ce2fcd53ee2c7bb2bfa941dcd1a955cca9c6c21a67a52e21f36.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "f171be00cad839712b79c06c966819dd0d3dab60766228ef1d4ebd366c529b67", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1a2a981d67761f80f5b32c483036c0fbbce45e21359382bf0eb80d70124cd43f", "generation_seconds_batch": 14.194926377036609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19662338495254517, "target_z": -0.4179687612872894, "ce": 5.863759994506836, "genuineness": 4.7834930419921875, "identity": 0.5318505764007568, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f171be00cad839712b79c06c966819dd0d3dab60766228ef1d4ebd366c529b67.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "f1f266f88a2c9e124fd54128dbedb82966fd05d467ccc72ae49f14467d3c72bf", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f8f17a8072a500a820f180a6cc430b3a0d7c4111d633da055576743f7271e4ea", "generation_seconds_batch": 19.55948807299137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.015768051147461, "target_z": 0.7499999575066753, "ce": 6.157639026641846, "genuineness": 4.582659721374512, "identity": 0.6842805743217468, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f1f266f88a2c9e124fd54128dbedb82966fd05d467ccc72ae49f14467d3c72bf.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "f1f64b6d14fa2ed8f1ac018fa469b9f0e42867fd2795034f6cefbbfd0dfface8", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4f14f0047517c66aa17ee4cafc3b1ef4cc8e273faa5a0cc2654cdff0848826b8", "generation_seconds_batch": 19.510900696041062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24319683015346527, "target_z": -0.35156250929541477, "ce": 6.1894097328186035, "genuineness": 4.494794845581055, "identity": 0.45807433128356934, "hypothesis": "The 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_Disappointment/f1f64b6d14fa2ed8f1ac018fa469b9f0e42867fd2795034f6cefbbfd0dfface8.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "f2107d9d4684b8658bbfa0473594e3e4d697fd6aef38d1c367c0a5ef67c88109", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a1a554f3d51eaef9936e03d7f9c76f349fc70cb37a9fe38dfd3a00bb6214d39", "generation_seconds_batch": 19.10833036492113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37058889865875244, "target_z": -0.16992188197156108, "ce": 5.7406487464904785, "genuineness": 4.846253395080566, "identity": 0.77166748046875, "hypothesis": "La porte 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_Disappointment/f2107d9d4684b8658bbfa0473594e3e4d697fd6aef38d1c367c0a5ef67c88109.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "5ea317773d6dc43d2544c93cbd72d55219c434dbd6f3198fd93511314f5c5a7c", "generation_seconds_batch": 14.609102912945673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21991011500358582, "target_z": -0.3847656246680209, "ce": 6.24500846862793, "genuineness": 4.419482707977295, "identity": 0.8203709125518799, "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_Disappointment/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.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": "f22736d47486008268640ce2720215065eee76d8d1c757bee34e4a8718c0e1e8", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd48ec605f45e005dd43c504a7c755a6a4db11f898ce9853bc732bbb182a5df4", "generation_seconds_batch": 19.29645399702713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.996590793132782, "target_z": 0.7226562679268713, "ce": 6.062326908111572, "genuineness": 4.394378662109375, "identity": 0.4951741397380829, "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_Disappointment/f22736d47486008268640ce2720215065eee76d8d1c757bee34e4a8718c0e1e8.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "f246a7207e7d0698996a53b74f03de4af13667f6552b5692837a0c0bf9a84b77", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0375f70172ca16977b3acabca262b74b9b7b622450f103e3277976e046a88803", "generation_seconds_batch": 19.786270234035328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11717456579208374, "target_z": -0.5312500159349968, "ce": 6.125868320465088, "genuineness": 4.6705241203308105, "identity": 0.7973805665969849, "hypothesis": "J'ai trouvé la 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_Disappointment/f246a7207e7d0698996a53b74f03de4af13667f6552b5692837a0c0bf9a84b77.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "f2a46aa0b4cce101be47f071724b60956a8063dddc8448305c2977a37c9b0b84", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "67e65f493e383d285d534dc07eb9564b6eeffaa5705406af9d889d6bd80b498e", "generation_seconds_batch": 20.990185511065647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11991420388221741, "target_z": -0.5273437320731287, "ce": 6.300607204437256, "genuineness": 4.758388519287109, "identity": 0.7485761046409607, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f2a46aa0b4cce101be47f071724b60956a8063dddc8448305c2977a37c9b0b84.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "f2e411ddaade098c8be8dc2b8dc19bde4a1bfdb73f2e082a283a4e4a8613ce92", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5828914d55c991df210dbe564e46a995e8065b17f77bcb5108262e0951ec33a5", "generation_seconds_batch": 22.704326160019264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1938837766647339, "target_z": -0.4218750026558328, "ce": 5.919358730316162, "genuineness": 4.406930446624756, "identity": 0.3043646514415741, "hypothesis": "The 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_Disappointment/f2e411ddaade098c8be8dc2b8dc19bde4a1bfdb73f2e082a283a4e4a8613ce92.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "f4b157f870968ea41d8c411f7189c4ad476c30deee19513ed4e61f29c4ea7bca", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "8691170ac356e2db2ab1be3989ad15c28d61c499c580e515b6237ccab3fb2c3d", "generation_seconds_batch": 22.191821706015617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059642672538757324, "target_z": -0.6132812546477074, "ce": 6.229123115539551, "genuineness": 4.770940780639648, "identity": 0.4491885304450989, "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_Disappointment/f4b157f870968ea41d8c411f7189c4ad476c30deee19513ed4e61f29c4ea7bca.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "f693a8c51a0ffb5e7c554f471b2c3041c65af1e60d0820fd051fc93f8b21a90f", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b74d317451c61f55c3e5d9d5442065d46e6535ec301244af44299841a67bc430", "generation_seconds_batch": 14.799304928979836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3692190945148468, "target_z": -0.1718750026558328, "ce": 6.109982967376709, "genuineness": 4.846253395080566, "identity": 0.7983827590942383, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce que cela 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_Disappointment/f693a8c51a0ffb5e7c554f471b2c3041c65af1e60d0820fd051fc93f8b21a90f.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "f6d32c6ad76cd37d76a7523c1d9dd77d87ed1690ae2d18ea366bfca25b33cbca", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e19ff14c0248eee2c963c8355f216cd96aef96d921dbfe401427a7b44625e829", "generation_seconds_batch": 19.30549704900477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.062382280826568604, "target_z": -0.609375013279164, "ce": 6.213237762451172, "genuineness": 4.607763767242432, "identity": 0.756242036819458, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f6d32c6ad76cd37d76a7523c1d9dd77d87ed1690ae2d18ea366bfca25b33cbca.mp3" }, { "id": "emo_Disappointment-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-1", "key": "f70fee2703968ffd24faf2b87d7f4d19134a8f96bad7b845567ded3a2fbc1fd4", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6747913f8e71cbf35a270db19dcda82b27777426d397807cb7ad074ef6483e96", "generation_seconds_batch": 14.467672514962032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21991011500358582, "target_z": -0.3847656246680209, "ce": 5.6334228515625, "genuineness": 4.833701133728027, "identity": 0.5321193933486938, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f70fee2703968ffd24faf2b87d7f4d19134a8f96bad7b845567ded3a2fbc1fd4.mp3" }, { "id": "emo_Disappointment-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-0", "key": "f71a242c3dd88b184f34ef88959b2c4dcc7503d95f0172563a337a2cabbb6ed6", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The door is still open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d897472d01e7979436db62c18ac46f39940fa10ba9c35ced5d6d9effd62477d4", "generation_seconds_batch": 22.75193816598039, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07334074378013611, "target_z": -0.5937500053116656, "ce": 6.221180438995361, "genuineness": 3.986435890197754, "identity": 0.1647063046693802, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f71a242c3dd88b184f34ef88959b2c4dcc7503d95f0172563a337a2cabbb6ed6.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "f77a0fc86c1026e1afbe85a374689710ae397d3d448f7020e3fb2ac8c0798a58", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "41d393072ac08efba04e0a7cc783a1ab210eeaaebfd7d462d47e41ab7cafc718", "generation_seconds_batch": 14.387616464984603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.65413898229599, "target_z": 0.23437499203250162, "ce": 6.165581703186035, "genuineness": 4.595211505889893, "identity": 0.6283984780311584, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f77a0fc86c1026e1afbe85a374689710ae397d3d448f7020e3fb2ac8c0798a58.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "8ed7d4475d96a7cf5edcbca19d56894b34372ea28c8e986ec34fa8cae8398eb0", "generation_seconds_batch": 14.645251529058442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1911441683769226, "target_z": -0.4257812440243762, "ce": 6.1894097328186035, "genuineness": 4.582659721374512, "identity": 0.7377372980117798, "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_Disappointment/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.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": "f7ebcd737193b939aeaa0d08deb3a44a77b037253aa74d837f68e0a561818153", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53bba5ddbce03ca42193c189f4e000056176b17a1a436bfd09b0a6370ffb15a6", "generation_seconds_batch": 19.30552566901315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4363396465778351, "target_z": -0.0761718766598955, "ce": 5.383228778839111, "genuineness": 4.055472373962402, "identity": 0.5164889693260193, "hypothesis": "De slotels liggen op de keukentafel. Je keken de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.18181818181818182, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f7ebcd737193b939aeaa0d08deb3a44a77b037253aa74d837f68e0a561818153.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_Disappointment", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": "85d9e5094d5fb062138708bbefac8d37d5b59c50503c7286efa9dbf4e4371281", "generation_seconds_batch": 16.008061555912718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20347243547439575, "target_z": -0.4082031153726061, "ce": 6.2767791748046875, "genuineness": 4.582659721374512, "identity": 0.5695621967315674, "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_Disappointment/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.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": "f8d1e1d08db7ea91de7ac6cf87eaeaac88cdf09be4e846605a5d17447bc1808b", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0673583a41a99ef97d9b6048600bfabd55871eace542278a7119cdab5f0bc1b0", "generation_seconds_batch": 15.224510548985563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1774053573608398, "target_z": 0.980468793157283, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.5776002407073975, "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_Disappointment/f8d1e1d08db7ea91de7ac6cf87eaeaac88cdf09be4e846605a5d17447bc1808b.mp3" }, { "id": "emo_Disappointment-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-1", "key": "f955cf0f6826ad3ffa3ab0b518df3902fbc9aab663ce8da9d26767b1e70cb260", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0a529d48e728c9f2333fed397c75574711c6607d7c288ac778cb2e043828b8ee", "generation_seconds_batch": 22.125738620990887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24593645334243774, "target_z": -0.347656246680209, "ce": 6.173524379730225, "genuineness": 4.6203155517578125, "identity": 0.42041558027267456, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f955cf0f6826ad3ffa3ab0b518df3902fbc9aab663ce8da9d26767b1e70cb260.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": "f97abde1f2a70e828998c71cbcb7ebf27a955f50671f3c304eedcca405622f52", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f33ac6378d8d231b80c8cb05bc305df5d5d22c71072dadf7f9d9947beefd8dd", "generation_seconds_batch": 19.24914996197913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23086857795715332, "target_z": -0.3691406167005225, "ce": 5.824047088623047, "genuineness": 4.632867813110352, "identity": 0.42344722151756287, "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_Disappointment/f97abde1f2a70e828998c71cbcb7ebf27a955f50671f3c304eedcca405622f52.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "f97fe20eb13da65e06a2aab5a181ded6502be3e0f56a4d796e01a4b3945e3c4a", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "272fed5305179ed16f36fc5adcc043e1cd905ec46f959fe07102396336279db9", "generation_seconds_batch": 19.318088673055172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07334074378013611, "target_z": -0.5937500053116656, "ce": 6.3641486167907715, "genuineness": 4.457139015197754, "identity": 0.5746892690658569, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f97fe20eb13da65e06a2aab5a181ded6502be3e0f56a4d796e01a4b3945e3c4a.mp3" }, { "id": "emo_Disappointment-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-0", "key": "f9c2b7ff8c57dff9d687afa332f17aa3d3abd70331a5e98fabc8172813874c1c", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1393ba54293e01ac21f4c3bc4fffb7824c746c085454a0fd0bcda823b9e2f762", "generation_seconds_batch": 19.248196749016643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2158007025718689, "target_z": -0.390624986720836, "ce": 6.046441555023193, "genuineness": 4.883909225463867, "identity": 0.7925993204116821, "hypothesis": "La porte 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_Disappointment/f9c2b7ff8c57dff9d687afa332f17aa3d3abd70331a5e98fabc8172813874c1c.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "f9d82726aae158145d79c9313ed8590108047f80371b64bd43585de77c5c6054", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c9c603c38f1304c6b39ebe7380967a261139c2291257deb2ff91547d51140c0d", "generation_seconds_batch": 20.971131057012826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6692068576812744, "target_z": 0.2558593620528151, "ce": 5.879645347595215, "genuineness": 4.6203155517578125, "identity": 0.7295722961425781, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/f9d82726aae158145d79c9313ed8590108047f80371b64bd43585de77c5c6054.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "fa2f32fb5753e3dca98f9d309cfd3b77796a289335b9d8a3b3ddf8adb0885e71", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "70b0384361b1a954628cc8db483240d7fe2eeed35d2eaecca5e08bb4987cf2aa", "generation_seconds_batch": 22.046711196075194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12265381217002869, "target_z": -0.5234374907045852, "ce": 6.078212261199951, "genuineness": 4.381826400756836, "identity": 0.6564019322395325, "hypothesis": "J'ai trouvé la 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_Disappointment/fa2f32fb5753e3dca98f9d309cfd3b77796a289335b9d8a3b3ddf8adb0885e71.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "fa77c2d15145cfc5b2d0e1859ab738304217b14c8384ac357459569b0d268b82", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "efcbd48f05b67992f20da888fa87f5200c21af068ed62eaab764c46e22ac22a6", "generation_seconds_batch": 19.31072629999835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27881181240081787, "target_z": -0.30078126527103854, "ce": 5.903473377227783, "genuineness": 4.582659721374512, "identity": 0.6164199113845825, "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_Disappointment/fa77c2d15145cfc5b2d0e1859ab738304217b14c8384ac357459569b0d268b82.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": "fa85179603846bbf445c16ada534d8d11830357afb349a08256438b015c208b8", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ef1ac531083300825c1e056b707f67b903d2824c7acb0d88d36c94289fd0e85c", "generation_seconds_batch": 14.43142698390875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.240457221865654, "target_z": -0.3554687506639582, "ce": 6.1894097328186035, "genuineness": 4.369274139404297, "identity": 0.4635833501815796, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/fa85179603846bbf445c16ada534d8d11830357afb349a08256438b015c208b8.mp3" }, { "id": "emo_Disappointment-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-1", "key": "fa929d02f908b5209f9d4eb1bf978f5002d9fa2716794ba7c768238aa42be816", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "346184d550c4e62c8a7e2de21e1852b91d12302ee118016dedd068d95bfdaabf", "generation_seconds_batch": 19.30549704900477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13909149169921875, "target_z": -0.5, "ce": 6.149696350097656, "genuineness": 4.582659721374512, "identity": 0.6262574195861816, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/fa929d02f908b5209f9d4eb1bf978f5002d9fa2716794ba7c768238aa42be816.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": "fac8a6355c5dbf8164def0402df7c3a2c7e866877723704f71e8ee5e7ea772e7", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "acf2359d078273ffff67bae5d35801f438a0f3afecf8dceeba286e704c506171", "generation_seconds_batch": 14.378284808946773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18840456008911133, "target_z": -0.4296874853929196, "ce": 5.831989288330078, "genuineness": 4.394378662109375, "identity": 0.35645997524261475, "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_Disappointment/fac8a6355c5dbf8164def0402df7c3a2c7e866877723704f71e8ee5e7ea772e7.mp3" }, { "id": "emo_Disappointment-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-es-0", "key": "fb06728a72e4565680fb2ff7e81e58e43f1011dae6da2f81df3adfe2aa6c6c24", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3939fb5ac3ccdbf41abb1527efb359b751c3557cc2e1a3af7738bbe42a4c9c8b", "generation_seconds_batch": 19.76903395401314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13909149169921875, "target_z": -0.5, "ce": 5.990842819213867, "genuineness": 4.218649387359619, "identity": 0.500769317150116, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/fb06728a72e4565680fb2ff7e81e58e43f1011dae6da2f81df3adfe2aa6c6c24.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "fbed59c6e3898edabe38640c934450b281190a53859b2ea0c0e796b3c2d932bb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e85136845508414e60a88aa916fad7b0b69025676f888b1c6a6867062c98431b", "generation_seconds_batch": 19.446914789034054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10073688626289368, "target_z": -0.554687506639582, "ce": 6.1020402908325195, "genuineness": 4.7081804275512695, "identity": 0.5321295261383057, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/fbed59c6e3898edabe38640c934450b281190a53859b2ea0c0e796b3c2d932bb.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "fc51ff877040e1cbf160b86e7494d920779a884dded71f127f212450c6562e96", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6bdf4fe9f4000798d841f3f17ea279a27c74c36b48a2643f662c16b91a0549b2", "generation_seconds_batch": 20.881567530101165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45688676834106445, "target_z": -0.04687498140917044, "ce": 6.125868320465088, "genuineness": 4.457139015197754, "identity": 0.6583810448646545, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/fc51ff877040e1cbf160b86e7494d920779a884dded71f127f212450c6562e96.mp3" }, { "id": "emo_Disappointment-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-nl-0", "key": "fcfd01cf5c58d7540cbf77e5c78f3bf78d4677d162e10b84e2f1e528564ac9ad", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7bd9d34726bfce88be24a2dcb576594bf8e77eade4b03d6cf9d292713f9db477", "generation_seconds_batch": 20.290116627933457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.240457221865654, "target_z": -0.3554687506639582, "ce": 5.8875885009765625, "genuineness": 4.545003414154053, "identity": 0.2736063599586487, "hypothesis": "De deur 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_Disappointment/fcfd01cf5c58d7540cbf77e5c78f3bf78d4677d162e10b84e2f1e528564ac9ad.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "fdb2ae9f7a020f8f6c930ab459ecf60764e10b95740c928042b7477b775b0b88", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9372dda24f232b7c241f0a5612885042c166b800a2381cfb3421583dbdbbe411", "generation_seconds_batch": 19.130495981080458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38154736161231995, "target_z": -0.1542968740040627, "ce": 5.895530700683594, "genuineness": 4.6705241203308105, "identity": 0.5234807729721069, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/fdb2ae9f7a020f8f6c930ab459ecf60764e10b95740c928042b7477b775b0b88.mp3" }, { "id": "emo_Disappointment-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-fr-1", "key": "fe4d11fb8b78965a925b1d122873001354a6a411aacf4bb82dea23e1d10decd8", "bucket": "emo_Disappointment", "phase": "wording", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6b4120764054aad797f5ab9834c579a8108148d244678f385c0811c1a52a3baf", "generation_seconds_batch": 15.717827829066664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11991420388221741, "target_z": -0.5273437320731287, "ce": 6.117925643920898, "genuineness": 4.7081804275512695, "identity": 0.777854323387146, "hypothesis": "J'ai trouvé la 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_Disappointment/fe4d11fb8b78965a925b1d122873001354a6a411aacf4bb82dea23e1d10decd8.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": "fe53457a071a885631f78aebac9c7a9f30cf8602263b7b2986399130a350cd1d", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ae1844384791ed19de4610cee42d18f01ff5d8e7c383b3271d8672f1f6dd2f6", "generation_seconds_batch": 14.40893407992553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7376972436904907, "target_z": 0.35351565122634887, "ce": 5.649308204650879, "genuineness": 4.507347106933594, "identity": 0.8039150238037109, "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_Disappointment/fe53457a071a885631f78aebac9c7a9f30cf8602263b7b2986399130a350cd1d.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": "ff3ea3ddd4ba8e77522f64006133aa0f76c9a15beb4bc0c7ab91a3790878e57f", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e01898432f1753b2b12e03e32a801ffaddd7f4a86318ffbb1703ab9da8fa30c", "generation_seconds_batch": 19.510038323001936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6609880328178406, "target_z": 0.24414063794718488, "ce": 5.307773113250732, "genuineness": 4.457139015197754, "identity": 0.59383225440979, "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_Disappointment/ff3ea3ddd4ba8e77522f64006133aa0f76c9a15beb4bc0c7ab91a3790878e57f.mp3" }, { "id": "emo_Disappointment-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-de-0", "key": "ff6dd68ac073b1e363d7bae3952202d3347d57bd376058877382fe73eb629bbb", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8fd7e380a5c77309bc6a7a291e9f8d2be3a80f9fcdfdaa4a81548dc241ae85bf", "generation_seconds_batch": 22.743774289032444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23223838210105896, "target_z": -0.3671874960162508, "ce": 6.332377910614014, "genuineness": 4.6705241203308105, "identity": 0.6155111789703369, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ff6dd68ac073b1e363d7bae3952202d3347d57bd376058877382fe73eb629bbb.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": "ffa84dd06e138bf8da104122068a23c3a0d6f256f729a8d45afa4065573f7196", "bucket": "emo_Disappointment", "phase": "heldout", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6ccdc78844be7cd1a25c7f60446fdb191813ac3a0cf39ec7a0632a18bb49b2d7", "generation_seconds_batch": 15.125352235976607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2541552782058716, "target_z": -0.33593752257457876, "ce": 5.681078910827637, "genuineness": 4.632867813110352, "identity": 0.6535271406173706, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ffa84dd06e138bf8da104122068a23c3a0d6f256f729a8d45afa4065573f7196.mp3" }, { "id": "emo_Disappointment-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Disappointment-en-1", "key": "ffaf8f5123977b07f11c781fecaf8223ad6999a2178b2a12af9c7a1c1cfa0456", "bucket": "emo_Disappointment", "phase": "grid", "candidate": "manual-3a61628184eb", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Introduce a hesitant, almost fragile texture to the voice. The energy should feel like it's leaking away rather than being actively suppressed.\nSCRIPT:\n(Begin with a slight hesitation, as if the speaker is gathering the courage to utter the words at all.) [3.2 seconds duration] I found the little box.\n(Maintain a breathy quality across the middle phrase, suggesting the effort of maintaining composure is draining.) [3.8 seconds duration] It was beside the old window.\n(Let the final inflection trail off into an almost inaudible whisper, signifying complete emotional exhaustion.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0b7a4d1b632bf13579e5c0e5756e03461021f17fe67d39475f7eb6d0ebf37c6a", "generation_seconds_batch": 19.854002356063575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07608035206794739, "target_z": -0.5898437639431222, "ce": 6.38003396987915, "genuineness": 4.482243061065674, "identity": 0.4161462187767029, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Disappointment/ffaf8f5123977b07f11c781fecaf8223ad6999a2178b2a12af9c7a1c1cfa0456.mp3" }, { "key": "original-emo_Disappointment-de-0-seed1701-scale0.0", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "d7b641f4cb31f674dc786b2b3635636706556d66568a2f3a0eb000417cf9116a", "task_id": "emo_Disappointment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.21854031085968018, "target_z": -0.3867187453522926, "ce": 6.173524379730225, "genuineness": 4.582659721374512, "identity": 0.5934622287750244, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/c7c12bc91257e9b1dce816b5.mp3" }, { "key": "original-emo_Disappointment-de-0-seed1701-scale0.5", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "875466a088323f67eca95a9e928eb59e0db7a7815373c4ed7a76843dd003b3d4", "task_id": "emo_Disappointment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.18840456008911133, "target_z": -0.4296874853929196, "ce": 6.316492557525635, "genuineness": 4.457139015197754, "identity": 0.46944788098335266, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/8d3e6995b925f19c9ace1bb6.mp3" }, { "key": "original-emo_Disappointment-de-0-seed1701-scale0.75", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "a038b423096b7f73f457f01aa0e63074e5c36ee9cddf1b9a83f250695e589757", "task_id": "emo_Disappointment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.2336081862449646, "target_z": -0.3652343753319791, "ce": 6.157639026641846, "genuineness": 4.3504462242126465, "identity": 0.6432715058326721, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/dc53be0936b6cac94caaa3c9.mp3" }, { "key": "original-emo_Disappointment-de-0-seed1701-scale1.0", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "f1fce77924b102efa5ab4f65e96659ba6037b377fe02213b3ee4bb339c08e0c5", "task_id": "emo_Disappointment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.19936299324035645, "target_z": -0.414062519918746, "ce": 6.23706579208374, "genuineness": 4.444586753845215, "identity": 0.5754121541976929, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/40d3f049c105bd8032345153.mp3" }, { "key": "original-emo_Disappointment-de-0-seed1702-scale0.0", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "a8024560a36d57c9ec82cd7619ce809e428e0daca1c9d5d190f0eb82f7083867", "task_id": "emo_Disappointment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.16785743832588196, "target_z": -0.45898438064364466, "ce": 6.086154937744141, "genuineness": 4.432034492492676, "identity": 0.2647281289100647, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/03781d32f4ca0919d9a5709e.mp3" }, { "key": "original-emo_Disappointment-de-0-seed1702-scale0.5", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "d11801f73e0f67e891713f3cb586483238ab584df562a074ffec105f12969d3a", "task_id": "emo_Disappointment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.17744609713554382, "target_z": -0.445312493360418, "ce": 6.268836498260498, "genuineness": 4.595211505889893, "identity": 0.45096153020858765, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/29f8a98486e2e80f126a699c.mp3" }, { "key": "original-emo_Disappointment-de-0-seed1702-scale0.75", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "54582cf05f4e102595b7bd5fd6efa22229717583ac34ecc12858a7381abae8d2", "task_id": "emo_Disappointment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.19251397252082825, "target_z": -0.4238281233401045, "ce": 6.054384231567383, "genuineness": 4.3504462242126465, "identity": 0.5852670073509216, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/e2f31cff60f551d4b7d67b89.mp3" }, { "key": "original-emo_Disappointment-de-0-seed1702-scale1.0", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "5ff3a519aa2ff6c4283d1e050a486c44c064bcdbc3d0721fe06e401e758cc1aa", "task_id": "emo_Disappointment-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.19936299324035645, "target_z": -0.414062519918746, "ce": 6.046441555023193, "genuineness": 4.344170093536377, "identity": 0.5499553680419922, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/80c060c52c1ce71c171583f5.mp3" }, { "key": "original-emo_Disappointment-de-1-seed1701-scale0.0", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "dad89b28bc9cbacc930ad0b986d22abcfdc2b8e13e05e2cf8bfe450abe51fc59", "task_id": "emo_Disappointment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.04594460129737854, "target_z": -0.6328125039837492, "ce": 6.38797664642334, "genuineness": 4.356721878051758, "identity": 0.5162886381149292, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/2c31a2d1d929fca857b0ed64.mp3" }, { "key": "original-emo_Disappointment-de-1-seed1701-scale0.5", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "9a587f73c1141f538ac77186b4823a67b56e64b75b8bfb77bc79fca36ac58ab4", "task_id": "emo_Disappointment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.026767313480377197, "target_z": -0.6601562360568778, "ce": 6.340320587158203, "genuineness": 4.193545341491699, "identity": 0.4649839699268341, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/3bfb9c6b58e8cb20e1cd110b.mp3" }, { "key": "original-emo_Disappointment-de-1-seed1701-scale0.75", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "0cc8713a54be747e3939fcbac011299edafc272a4efaaf0f513641a8a8155053", "task_id": "emo_Disappointment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.10073688626289368, "target_z": -0.554687506639582, "ce": 6.38797664642334, "genuineness": 4.362998008728027, "identity": 0.5478882789611816, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/7873139806ae6dfee38761e2.mp3" }, { "key": "original-emo_Disappointment-de-1-seed1701-scale1.0", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "fd32fb2fb083d6a39a2deb99aa191460279efc89a0f975a48b4d671b854cf335", "task_id": "emo_Disappointment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.013069242238998413, "target_z": -0.6796874853929197, "ce": 6.38003396987915, "genuineness": 4.2249250411987305, "identity": 0.5389935970306396, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/464e76cc1d29b93c6178f12e.mp3" }, { "key": "original-emo_Disappointment-de-1-seed1702-scale0.0", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "a5c2ca600f4f8f5b102337f079d9ae7458eafe1e40c9ccf1d0c9db88b5f6c2da", "task_id": "emo_Disappointment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.06512191891670227, "target_z": -0.6054687294172958, "ce": 6.459460258483887, "genuineness": 4.193545341491699, "identity": 0.5213186740875244, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/079ba42a940c808ba18aff2f.mp3" }, { "key": "original-emo_Disappointment-de-1-seed1702-scale0.5", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "4c77be9aac3cbbe9c8c00b3dd5e8826ed03ac0500c09d564b4e23686b0345935", "task_id": "emo_Disappointment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.002110779285430908, "target_z": -0.695312493360418, "ce": 6.403861999511719, "genuineness": 4.281409740447998, "identity": 0.36195001006126404, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/8307bf44e32b0af2721543fe.mp3" }, { "key": "original-emo_Disappointment-de-1-seed1702-scale0.75", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "1709aee778b7a89aadca166fe7e6af67a08028efc9f2c583949b8f42dee5cfb1", "task_id": "emo_Disappointment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.04594460129737854, "target_z": -0.6328125039837492, "ce": 6.284721851348877, "genuineness": 4.20609712600708, "identity": 0.7226566672325134, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/8218f38453ba6b9d368d81f9.mp3" }, { "key": "original-emo_Disappointment-de-1-seed1702-scale1.0", "bucket": "emo_Disappointment", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "fdf01716e0fa3338c0aae99623a944cc9dcc132190fe37811a6166d85d57e8e8", "task_id": "emo_Disappointment-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.06786152720451355, "target_z": -0.6015624880487525, "ce": 6.38797664642334, "genuineness": 4.331617832183838, "identity": 0.5681066513061523, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/de/ef5e606ad5e81e2e39ed6c2e.mp3" }, { "key": "original-emo_Disappointment-en-0-seed1701-scale0.0", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "2330274782f9d64047e880de1fb66ebb369c92494e57093c142a0d804fdc86ac", "task_id": "emo_Disappointment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.08977842330932617, "target_z": -0.5703125146070803, "ce": 6.205295085906982, "genuineness": 4.344170093536377, "identity": 0.3641161322593689, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/2d8e0c169df45bf251959254.mp3" }, { "key": "original-emo_Disappointment-en-0-seed1701-scale0.5", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "78a39bbae9f991d3eeb081e62226aab6115b208243182990e0ed8f56fe22c30d", "task_id": "emo_Disappointment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.1801857054233551, "target_z": -0.4414062519918746, "ce": 6.324435234069824, "genuineness": 4.124508857727051, "identity": 0.3536011874675751, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/6b060733970fd85de129085d.mp3" }, { "key": "original-emo_Disappointment-en-0-seed1701-scale0.75", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "0a850b799495b3d23c91619735de8e337e8b404737c3ba0d6b4baaeb442738a3", "task_id": "emo_Disappointment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 6.022613525390625, "genuineness": 3.948779582977295, "identity": 0.39656925201416016, "hypothesis": "The 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_Disappointment/en/0483f17c496c73495ca62cd7.mp3" }, { "key": "original-emo_Disappointment-en-0-seed1701-scale1.0", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "78c1a7a651f146ee63094c3d5e6f5fa97e7e478eb8c452a9665b5ce64e69fe1e", "task_id": "emo_Disappointment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.16100841760635376, "target_z": -0.46874998406500323, "ce": 6.173524379730225, "genuineness": 4.13078498840332, "identity": 0.3674359619617462, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/244923e0ef8106479284d873.mp3" }, { "key": "original-emo_Disappointment-en-0-seed1702-scale0.0", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "d94aa304db18211635c280a930bed5d6e0e1f5116ba0f3472b89199b07f66e1a", "task_id": "emo_Disappointment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.226759135723114, "target_z": -0.3750000212466624, "ce": 6.109982967376709, "genuineness": 4.18726921081543, "identity": 0.13874205946922302, "hypothesis": "The 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_Disappointment/en/4c99e574ef84cd24e37e655d.mp3" }, { "key": "original-emo_Disappointment-en-0-seed1702-scale0.5", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "56483762901d73c24cd0691e9e58a2def98bd0b4fdcd64e2c8aafe0f4e118c84", "task_id": "emo_Disappointment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11991420388221741, "target_z": -0.5273437320731287, "ce": 6.181467056274414, "genuineness": 3.9676074981689453, "identity": 0.2017645537853241, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/159d71199fe77ef25418c715.mp3" }, { "key": "original-emo_Disappointment-en-0-seed1702-scale0.75", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "7709f77ce4ee0d1e5cfb599ef346b5d68984b0d5deb90ae34cc4870d7c13414a", "task_id": "emo_Disappointment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.18429511785507202, "target_z": -0.4355468899390595, "ce": 6.086154937744141, "genuineness": 3.8044304847717285, "identity": 0.438785195350647, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/aa5c2669f0d58e5260ae444e.mp3" }, { "key": "original-emo_Disappointment-en-0-seed1702-scale1.0", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "a499c072353f5944325da486734be7155f028f16118629b56a17e9883b1f67ac", "task_id": "emo_Disappointment-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 6.117925643920898, "genuineness": 3.8044304847717285, "identity": 0.27341192960739136, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/aa046ae4bdb60daefa98abee.mp3" }, { "key": "original-emo_Disappointment-en-1-seed1701-scale0.0", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "27102cf87463da2ae2f95d775bf7800cf4f1b851aa089a771e508fb37328a195", "task_id": "emo_Disappointment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": -0.008847683668136597, "target_z": -0.7109375013279164, "ce": 6.324435234069824, "genuineness": 4.482243061065674, "identity": 0.25450360774993896, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/f206b329a284d5710b780170.mp3" }, { "key": "original-emo_Disappointment-en-1-seed1701-scale0.5", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "279ddedd40da0cfcb95bd8fe8621a68a8ee4bba80f60d47de9f600c550959278", "task_id": "emo_Disappointment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 6.332377910614014, "genuineness": 4.457139015197754, "identity": 0.33475983142852783, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/941213d4df326fecc5f52d38.mp3" }, { "key": "original-emo_Disappointment-en-1-seed1701-scale0.75", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "31f3b2466d707d464fa55fd7d678f9ecd685c7849f28d9a753da2c2bbb9369c8", "task_id": "emo_Disappointment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.029506921768188477, "target_z": -0.6562499946883344, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.4465476870536804, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/6be8f55ebbf39089c94e1f53.mp3" }, { "key": "original-emo_Disappointment-en-1-seed1701-scale1.0", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "1466c21271d2a10fa78f9074adc1e2177959f1bac28a32d0599b2ef001f76f18", "task_id": "emo_Disappointment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 6.3641486167907715, "genuineness": 4.557555198669434, "identity": 0.36290305852890015, "hypothesis": "I found a 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/audio/emo_Disappointment/en/7907f7b70ff85ee030c5472f.mp3" }, { "key": "original-emo_Disappointment-en-1-seed1702-scale0.0", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "1a13c83c4ceb39c100250d6515a445ecd6355b2c329c36536b8d14fc6cd2f898", "task_id": "emo_Disappointment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11443495750427246, "target_z": -0.5351562573035402, "ce": 6.2767791748046875, "genuineness": 4.457139015197754, "identity": 0.5671655535697937, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/e4ae0ef691a7226c12621154.mp3" }, { "key": "original-emo_Disappointment-en-1-seed1702-scale0.5", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "a8c2c541bebb186807f435058ff80d8dd26cad437cc494133174ea7bdc300f8c", "task_id": "emo_Disappointment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.1089557409286499, "target_z": -0.542968740040627, "ce": 6.308549880981445, "genuineness": 4.331617832183838, "identity": 0.21133293211460114, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/8d59171be4368b8eed43698d.mp3" }, { "key": "original-emo_Disappointment-en-1-seed1702-scale0.75", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "2e66c8a4cefcc5209fb6914dfa26cf8107ed53efa5ac2175d3f6c506928654b0", "task_id": "emo_Disappointment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 6.300607204437256, "genuineness": 4.375550270080566, "identity": 0.38009119033813477, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/bf4cc658e1730fa2f5165974.mp3" }, { "key": "original-emo_Disappointment-en-1-seed1702-scale1.0", "bucket": "emo_Disappointment", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "42c179ac6c763da407a1a9d0f99826e0abb06988b47d79a92d3e393ab4d4dd0e", "task_id": "emo_Disappointment-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.056903064250946045, "target_z": -0.6171874960162508, "ce": 6.340320587158203, "genuineness": 4.262581825256348, "identity": 0.6162246465682983, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/en/35920947d5fdfcac2f41cd98.mp3" }, { "key": "original-emo_Disappointment-es-0-seed1701-scale0.0", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "32724dfd334e4a68f1509b47fe1ca2e9f6358c6ac63cfe934e51b52bf64ba033", "task_id": "emo_Disappointment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.13087263703346252, "target_z": -0.511718766598955, "ce": 6.165581703186035, "genuineness": 4.193545341491699, "identity": 0.3830466568470001, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/696a1aff6fd488346803d6fe.mp3" }, { "key": "original-emo_Disappointment-es-0-seed1701-scale0.5", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "a42546f5a5f98bb3740ca84f198b6fc3440d664705001cb6c19ed49f4f40f3b3", "task_id": "emo_Disappointment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.21717050671577454, "target_z": -0.38867186603656434, "ce": 5.998785495758057, "genuineness": 4.482243061065674, "identity": 0.593579888343811, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/e39275c59ce9d774e5ca307c.mp3" }, { "key": "original-emo_Disappointment-es-0-seed1701-scale0.75", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "66c463569b666af538eec9b842c4cd87bc89870d7b17c08195cb9d35eb017cdd", "task_id": "emo_Disappointment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 5.95112943649292, "genuineness": 3.8922953605651855, "identity": 0.4017683267593384, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/9e2df9ebbbbe7fbb102a75d0.mp3" }, { "key": "original-emo_Disappointment-es-0-seed1701-scale1.0", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "76443c6d02ae1d2d25edb0b7494c8c19d9e29dd70e85fcd1d5bad7389f6fe2c9", "task_id": "emo_Disappointment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.07881999015808105, "target_z": -0.585937480081254, "ce": 6.205295085906982, "genuineness": 4.469690799713135, "identity": 0.5520220994949341, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/357615c3e3654ad869363041.mp3" }, { "key": "original-emo_Disappointment-es-0-seed1702-scale0.0", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "04cd61d6e4adfcd625c931cbe0926cff1839705c43c89c1be7e5d49f18218ce6", "task_id": "emo_Disappointment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.08429920673370361, "target_z": -0.5781249973441672, "ce": 6.046441555023193, "genuineness": 4.2374773025512695, "identity": 0.2578169107437134, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/96632e3a3ed3353a3920ea2c.mp3" }, { "key": "original-emo_Disappointment-es-0-seed1702-scale0.5", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "dd3002b07f991928ed145b0afdf09dd6f7acdb65a9d59a88ed80d6f14bba88a4", "task_id": "emo_Disappointment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.12265381217002869, "target_z": -0.5234374907045852, "ce": 5.863759994506836, "genuineness": 3.9173994064331055, "identity": 0.5642044544219971, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/480acee661222ecebb0e8047.mp3" }, { "key": "original-emo_Disappointment-es-0-seed1702-scale0.75", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "376a288d31ff70cd7b28aba4efbb1f9d96a762bb160337dab3a8c16c5355ff5a", "task_id": "emo_Disappointment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.1514197587966919, "target_z": -0.4824218713482299, "ce": 6.086154937744141, "genuineness": 4.300237655639648, "identity": 0.6644114255905151, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/61ec06743656f9d5c76d384b.mp3" }, { "key": "original-emo_Disappointment-es-0-seed1702-scale1.0", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "838d9fa26b54076a6e6e0fe7c69ab86a32b82c42a585cc2f739c4f44e640c7b9", "task_id": "emo_Disappointment-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.15689897537231445, "target_z": -0.4746093886111431, "ce": 5.8875885009765625, "genuineness": 3.8169827461242676, "identity": 0.6378459334373474, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/6eb9b427bb4cd4d7516c0d43.mp3" }, { "key": "original-emo_Disappointment-es-1-seed1701-scale0.0", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "de6be604ae697e22756de3fee338a52e2ba330e83e0c0e271486e5d8b0c23526", "task_id": "emo_Disappointment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.15415936708450317, "target_z": -0.4785156299796865, "ce": 5.8875885009765625, "genuineness": 4.607763767242432, "identity": 0.7330475449562073, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/2c6737d0eaf84028a30c011b.mp3" }, { "key": "original-emo_Disappointment-es-1-seed1701-scale0.5", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "b54c8d6d0ca8bc59ef7b4ecf18612948580e4ac871375b886acb8a2778e7ed7a", "task_id": "emo_Disappointment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.054163455963134766, "target_z": -0.6210937373847942, "ce": 6.165581703186035, "genuineness": 4.557555198669434, "identity": 0.6268733739852905, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/e3f5bfeb220e67da3f3399ad.mp3" }, { "key": "original-emo_Disappointment-es-1-seed1701-scale0.75", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "9a10bcc395a558f4a0f6be63d281cf482220a1bdada58b589621c1d5f3693f91", "task_id": "emo_Disappointment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 6.23706579208374, "genuineness": 4.7081804275512695, "identity": 0.5558156371116638, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/6e945b8e3077cad29209e239.mp3" }, { "key": "original-emo_Disappointment-es-1-seed1701-scale1.0", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "0cea1c608ccd28593aa39847a5b45759265a53de9e64a818d327aa669c94ec75", "task_id": "emo_Disappointment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.10347649455070496, "target_z": -0.5507812652710385, "ce": 6.149696350097656, "genuineness": 4.6203155517578125, "identity": 0.5165663957595825, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/5d821042e623c05a07361205.mp3" }, { "key": "original-emo_Disappointment-es-1-seed1702-scale0.0", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "57d380b23a4ad2406570269de7fe0c165d3a42b3b358838298165abb18b741ee", "task_id": "emo_Disappointment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.1514197587966919, "target_z": -0.4824218713482299, "ce": 6.046441555023193, "genuineness": 4.582659721374512, "identity": 0.612966001033783, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/297cabb5787765a9e3cc6ba7.mp3" }, { "key": "original-emo_Disappointment-es-1-seed1702-scale0.5", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "2cdc2595e1dc5ffa9f059f512b25cb62e987793a64f564cbe75d71432bf8204f", "task_id": "emo_Disappointment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.10073688626289368, "target_z": -0.554687506639582, "ce": 6.24500846862793, "genuineness": 4.7834930419921875, "identity": 0.5759044289588928, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/bc23b9f66ed56eece3fe9b25.mp3" }, { "key": "original-emo_Disappointment-es-1-seed1702-scale0.75", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "85d60eaa25cc08b23a31e556aceb2211d1e7fe7852bbd981e7ac6bd2c6c624f4", "task_id": "emo_Disappointment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.1692272424697876, "target_z": -0.457031259959373, "ce": 6.109982967376709, "genuineness": 4.570107460021973, "identity": 0.599913477897644, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/d3cc7db866bafd787a141c4e.mp3" }, { "key": "original-emo_Disappointment-es-1-seed1702-scale1.0", "bucket": "emo_Disappointment", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "7b1424de50537eb6795b7d9a082b319232a790bb0b899a0ee832ce46f0f0e2e8", "task_id": "emo_Disappointment-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.16511783003807068, "target_z": -0.4628906220121881, "ce": 6.205295085906982, "genuineness": 4.557555198669434, "identity": 0.7863994240760803, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/es/4837aceb9e9e0db103fc2c9e.mp3" }, { "key": "original-emo_Disappointment-fr-0-seed1701-scale0.0", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "e1ebfad5ef91800181cc04b3a6937fdc1fcef9ec33140ab15019b6ecb9f170f1", "task_id": "emo_Disappointment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.18840456008911133, "target_z": -0.4296874853929196, "ce": 6.205295085906982, "genuineness": 4.369274139404297, "identity": 0.6640244722366333, "hypothesis": "La porte 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_Disappointment/fr/60d37fb2ae88ca00513b490c.mp3" }, { "key": "original-emo_Disappointment-fr-0-seed1701-scale0.5", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "064ce458ded8c629b90af78002ff8384fee94605533be6d45cb42ed95d6bdeae", "task_id": "emo_Disappointment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.2089516520500183, "target_z": -0.4003906326355193, "ce": 6.165581703186035, "genuineness": 4.532451152801514, "identity": 0.8156546950340271, "hypothesis": "La porte 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_Disappointment/fr/344336bc25a821449d6cb59d.mp3" }, { "key": "original-emo_Disappointment-fr-0-seed1701-scale0.75", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "cc360a0023fb3889cf302148dacbc17dbcf53c3238b9a332646f029205a9a156", "task_id": "emo_Disappointment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.1623782217502594, "target_z": -0.4667968633807315, "ce": 6.09409761428833, "genuineness": 4.287685871124268, "identity": 0.7734788656234741, "hypothesis": "La porte 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_Disappointment/fr/618b9fc4e9a90f1dcaedf416.mp3" }, { "key": "original-emo_Disappointment-fr-0-seed1701-scale1.0", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "26498987848b3efa72dc1e8a4fdbece35d0e02f0a439d7ed31cd155cc0d9c789", "task_id": "emo_Disappointment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.21717050671577454, "target_z": -0.38867186603656434, "ce": 6.006728172302246, "genuineness": 4.293961524963379, "identity": 0.6780158281326294, "hypothesis": "La porte 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_Disappointment/fr/386b16807637ac5905f46bbb.mp3" }, { "key": "original-emo_Disappointment-fr-0-seed1702-scale0.0", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "a22ba5863259e48dce9b9356dc1cb9bf1e0e79c58c0ea352c24b0281f89bed72", "task_id": "emo_Disappointment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.18429511785507202, "target_z": -0.4355468899390595, "ce": 5.982900142669678, "genuineness": 4.331617832183838, "identity": 0.8058478832244873, "hypothesis": "La porte 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_Disappointment/fr/649034cac5cc1581296c698a.mp3" }, { "key": "original-emo_Disappointment-fr-0-seed1702-scale0.5", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "a7712373619d39d9f96103592279d136cd1fd1cab7a98ef06afcfa67d741e276", "task_id": "emo_Disappointment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.20073282718658447, "target_z": -0.4121093567411495, "ce": 6.141753673553467, "genuineness": 4.337893962860107, "identity": 0.7478656768798828, "hypothesis": "La porte 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_Disappointment/fr/4fe7e0eb7ece0fb5c58e78ba.mp3" }, { "key": "original-emo_Disappointment-fr-0-seed1702-scale0.75", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "e85aa6b0ee04f16079d9e2fdbab0d4aa7e1dd40c6b86cfb39e5a9f26764a5c5d", "task_id": "emo_Disappointment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.16511783003807068, "target_z": -0.4628906220121881, "ce": 6.133810997009277, "genuineness": 4.18099308013916, "identity": 0.6086759567260742, "hypothesis": "La porte 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_Disappointment/fr/95cdfa6c76b6c4b464e2fc31.mp3" }, { "key": "original-emo_Disappointment-fr-0-seed1702-scale1.0", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "40c59f5db0d5bb76ff4df09b4694912a2e1ddba69caf36ccaa52c5c4bf5da11f", "task_id": "emo_Disappointment-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.21306106448173523, "target_z": -0.39453127058270415, "ce": 5.974957466125488, "genuineness": 4.406930446624756, "identity": 0.7623690962791443, "hypothesis": "La porte 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_Disappointment/fr/cf260d7dd40f2d94db14b540.mp3" }, { "key": "original-emo_Disappointment-fr-1-seed1701-scale0.0", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "90128cba6786a52383ffc5baeb04cc2ee35bc3efe8b7cf06655430368c951c41", "task_id": "emo_Disappointment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.08977842330932617, "target_z": -0.5703125146070803, "ce": 6.09409761428833, "genuineness": 4.545003414154053, "identity": 0.7281494140625, "hypothesis": "J'ai trouvé la 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_Disappointment/fr/6e9042f9ce1b5a3a5ba6a945.mp3" }, { "key": "original-emo_Disappointment-fr-1-seed1701-scale0.5", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "dffcc2c5a4c6d841f5c781133ad9305bb064f182e1d928158f49ea3b54de9410", "task_id": "emo_Disappointment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.10073688626289368, "target_z": -0.554687506639582, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.590908944606781, "hypothesis": "J'ai trouvé la 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_Disappointment/fr/21e7c419b36cd5088d024d5a.mp3" }, { "key": "original-emo_Disappointment-fr-1-seed1701-scale0.75", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "e285becd60ca47defeccdf8e4132568f844b42a2547303f399d343e7a1319e15", "task_id": "emo_Disappointment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.1336122751235962, "target_z": -0.5078124827370868, "ce": 6.078212261199951, "genuineness": 4.557555198669434, "identity": 0.8535177707672119, "hypothesis": "J'ai trouvé la 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_Disappointment/fr/b5e09a29fe898f6426beb346.mp3" }, { "key": "original-emo_Disappointment-fr-1-seed1701-scale1.0", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "ba79686ef3947f5052bb5c674f48a07bc0b06a5a3fa49895723345cfa37c54eb", "task_id": "emo_Disappointment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11169534921646118, "target_z": -0.5390624986720836, "ce": 5.959072113037109, "genuineness": 4.557555198669434, "identity": 0.7562638521194458, "hypothesis": "J'ai trouvé la 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_Disappointment/fr/4d66916eeae2daf14606a675.mp3" }, { "key": "original-emo_Disappointment-fr-1-seed1702-scale0.0", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "82cd364217f529d893f086f432a2917fac411a0a89de33c0eed21c2f29a5d9e1", "task_id": "emo_Disappointment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.08977842330932617, "target_z": -0.5703125146070803, "ce": 6.157639026641846, "genuineness": 4.256305694580078, "identity": 0.7082153558731079, "hypothesis": "J'ai trouvé la 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_Disappointment/fr/3d70cfdad21a3f3a58bbeed8.mp3" }, { "key": "original-emo_Disappointment-fr-1-seed1702-scale0.5", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "d44d29ad01f834f86fbd910ae1939a3b40feea1f00532edfc3f07e1c9a9a6b54", "task_id": "emo_Disappointment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.04594460129737854, "target_z": -0.6328125039837492, "ce": 6.173524379730225, "genuineness": 4.3504462242126465, "identity": 0.6231223344802856, "hypothesis": "J'ai trouvé la 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_Disappointment/fr/008981bb5b9a1841fe820643.mp3" }, { "key": "original-emo_Disappointment-fr-1-seed1702-scale0.75", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "7123a5c5f5645b2f5313defea8418aa1446edda389927111eed2a41cc9921cbc", "task_id": "emo_Disappointment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11717456579208374, "target_z": -0.5312500159349968, "ce": 6.0146708488464355, "genuineness": 4.2374773025512695, "identity": 0.7854079008102417, "hypothesis": "J'ai trouvé la 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_Disappointment/fr/547ad7e02319b9447a61909f.mp3" }, { "key": "original-emo_Disappointment-fr-1-seed1702-scale1.0", "bucket": "emo_Disappointment", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "01776996c22a9ee44cad298ba78a18e4b9174669884b0be644d25569d09ecb7e", "task_id": "emo_Disappointment-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.11717456579208374, "target_z": -0.5312500159349968, "ce": 6.125868320465088, "genuineness": 4.413206577301025, "identity": 0.7396342754364014, "hypothesis": "J'ai trouvé la 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_Disappointment/fr/aaf61dd27c950252567f1298.mp3" }, { "key": "original-emo_Disappointment-nl-0-seed1701-scale0.0", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "34df55d5c71b8fae3b8561ba8756371617275327515e8a9d34703ccd177026ec", "task_id": "emo_Disappointment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.2829212546348572, "target_z": -0.29492186072489873, "ce": 5.998785495758057, "genuineness": 4.293961524963379, "identity": 0.6651963591575623, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/6bac67656a6bfd1abf40046e.mp3" }, { "key": "original-emo_Disappointment-nl-0-seed1701-scale0.5", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "f52b00df41f7fd82af9f1af529c80082ff2e51c962743459bd71fa06c6307fbb", "task_id": "emo_Disappointment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.18155550956726074, "target_z": -0.4394531313076029, "ce": 6.117925643920898, "genuineness": 3.898571252822876, "identity": 0.7498357892036438, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/1b9b6ad9170e80cb541ab686.mp3" }, { "key": "original-emo_Disappointment-nl-0-seed1701-scale0.75", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "bce3bbc564777ef1cd9a81850be34a14fc52d6c32de919de887e75875bc1db0f", "task_id": "emo_Disappointment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.2555251121520996, "target_z": -0.33398435939698234, "ce": 6.117925643920898, "genuineness": 4.337893962860107, "identity": 0.6106500625610352, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/e332ae842e3c1f0ef6d4a83c.mp3" }, { "key": "original-emo_Disappointment-nl-0-seed1701-scale1.0", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "5afd00d9a966f5fb3f0fc23eb1d187341c8d6cdabcf9cfb282e79fcbe7010dec", "task_id": "emo_Disappointment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.18566492199897766, "target_z": -0.43359376925478776, "ce": 5.895530700683594, "genuineness": 4.293961524963379, "identity": 0.6575782299041748, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/51db1e049634c9d48e996611.mp3" }, { "key": "original-emo_Disappointment-nl-0-seed1702-scale0.0", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "2e9ba29c331952f45dcbeb6ab9468dbe31a4f5c088f322a573223c81138d75e5", "task_id": "emo_Disappointment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.2226497232913971, "target_z": -0.3808593832994775, "ce": 5.998785495758057, "genuineness": 4.250029563903809, "identity": 0.5179182291030884, "hypothesis": "De deur 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_Disappointment/nl/a48ec45280f58e5bdc66643b.mp3" }, { "key": "original-emo_Disappointment-nl-0-seed1702-scale0.5", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "dcccd81de04cfa7c96460fcfcc363b8a2bf687e795e2f6a1062da35e28813df9", "task_id": "emo_Disappointment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.23771759867668152, "target_z": -0.359375013279164, "ce": 6.0146708488464355, "genuineness": 4.080576419830322, "identity": 0.7330365180969238, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/ec016c448e4eb0956f2c5c7c.mp3" }, { "key": "original-emo_Disappointment-nl-0-seed1702-scale0.75", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "d378a7829764eb9eaf16d4bd4bb499a4b531d902c6fbe80a1387292606d0b75d", "task_id": "emo_Disappointment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.18977436423301697, "target_z": -0.4277343647086479, "ce": 6.0146708488464355, "genuineness": 4.20609712600708, "identity": 0.64095139503479, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/adc7af145f801e0c429adda0.mp3" }, { "key": "original-emo_Disappointment-nl-0-seed1702-scale1.0", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "374ee470b1c01112ad2755332206ae5a16547af0da4b812cdbc84978616fd546", "task_id": "emo_Disappointment-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.4370245635509491, "target_z": -0.07519529507109728, "ce": 6.133810997009277, "genuineness": 4.256305694580078, "identity": 0.6005222797393799, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/c7010de3314e5c42fd7e2440.mp3" }, { "key": "original-emo_Disappointment-nl-1-seed1701-scale0.0", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "df7a6bf7e6405341f85b841a7cc2e54c6684ff79ee9fe8c635deb10695fb2544", "task_id": "emo_Disappointment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.1911441683769226, "target_z": -0.4257812440243762, "ce": 6.149696350097656, "genuineness": 4.030367851257324, "identity": 0.3814889192581177, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/9ab74b79ffec57748b96d2e2.mp3" }, { "key": "original-emo_Disappointment-nl-1-seed1701-scale0.5", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "97d2e6c4bc827f933030d9ca858a9da48451dc899706f11bb7ec45d2bc66b75c", "task_id": "emo_Disappointment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.23223838210105896, "target_z": -0.3671874960162508, "ce": 6.078212261199951, "genuineness": 4.256305694580078, "identity": 0.5750443935394287, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/8d6393bbd4461214a1cf89dd.mp3" }, { "key": "original-emo_Disappointment-nl-1-seed1701-scale0.75", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "1913db5f6b6b61b98e84f99eeb7800eada85ba128c0032c5615aedb6d31349e8", "task_id": "emo_Disappointment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.22127991914749146, "target_z": -0.3828125039837492, "ce": 6.1894097328186035, "genuineness": 4.15588903427124, "identity": 0.642423152923584, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/75379705cecd0a2b5fb8cf51.mp3" }, { "key": "original-emo_Disappointment-nl-1-seed1701-scale1.0", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "10d9dd5ff6cfa10fca0abae1a7c1184c0e632b8c7720442f7d7932d8f133e877", "task_id": "emo_Disappointment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.21991011500358582, "target_z": -0.3847656246680209, "ce": 6.157639026641846, "genuineness": 4.2249250411987305, "identity": 0.8223185539245605, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/fbaa334b1356e9a8fa115245.mp3" }, { "key": "original-emo_Disappointment-nl-1-seed1702-scale0.0", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "afde7ca91d54c081fc6202f14f3d4ea0309740ba58cd96c7a116b9ca4d38698f", "task_id": "emo_Disappointment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.21854031085968018, "target_z": -0.3867187453522926, "ce": 6.268836498260498, "genuineness": 4.218649387359619, "identity": 0.6897826194763184, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude sataraam. 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_Disappointment/nl/99ba82bd8e0ad8f14a668b0e.mp3" }, { "key": "original-emo_Disappointment-nl-1-seed1702-scale0.5", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "25eb61b2f2ac0264f2a5cd1da1d2f2b75495286c182f2ceb44aaad3160ee00ba", "task_id": "emo_Disappointment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.16648763418197632, "target_z": -0.4609375013279164, "ce": 6.1020402908325195, "genuineness": 4.3127899169921875, "identity": 0.578513503074646, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/1085b67d826254de5554d224.mp3" }, { "key": "original-emo_Disappointment-nl-1-seed1702-scale0.75", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "424633d643d777af8044af6d45be9bf970cdc44ab85adb17d6f871d22013a720", "task_id": "emo_Disappointment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.21717050671577454, "target_z": -0.38867186603656434, "ce": 6.125868320465088, "genuineness": 4.394378662109375, "identity": 0.5336748957633972, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/30696426706a2ba0d86b64b7.mp3" }, { "key": "original-emo_Disappointment-nl-1-seed1702-scale1.0", "bucket": "emo_Disappointment", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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 Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "88ccbf0fe842ed9b05761156d023ab12f54ec4ddc41a810934fa3d0321ac6401", "mp3_sha256": "cfb347c55a5eb813e565a8fc61e81bf439bee481f0c1b38c69ca772ffaa90337", "task_id": "emo_Disappointment-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Disappointment. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Disappointment. 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 Disappointment. 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 Disappointment. 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": 0.21443089842796326, "target_z": -0.39257810740510773, "ce": 6.070269584655762, "genuineness": 4.256305694580078, "identity": 0.48772740364074707, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Disappointment/nl/01a134b5610072382d2e2e5e.mp3" } ], "source_standard_audio_unchanged": true }